├── .gitignore ├── LICENSE ├── README.md ├── docs ├── Makefile ├── conf.py ├── index.rst └── user │ ├── cluster.rst │ ├── cluster_1.png │ ├── cluster_2.png │ ├── cluster_3.png │ ├── experiments.rst │ ├── gym_integration.rst │ ├── implement_algo_advanced.rst │ ├── implement_algo_basic.rst │ ├── implement_env.rst │ └── installation.rst ├── environment.yml ├── examples ├── __init__.py ├── cluster_demo.py ├── cluster_gym_mujoco_demo.py ├── ddpg_cartpole.py ├── nop_cartpole.py ├── point_env.py ├── trpo_cartpole.py ├── trpo_cartpole_pickled.py ├── trpo_cartpole_recurrent.py ├── trpo_gym_cartpole.py ├── trpo_gym_pendulum.py ├── trpo_gym_tf_cartpole.py ├── trpo_point.py ├── trpo_swimmer.py ├── vpg_1.py └── vpg_2.py ├── rllab ├── __init__.py ├── algos │ ├── __init__.py │ ├── base.py │ ├── batch_polopt.py │ ├── cem.py │ ├── cma_es.py │ ├── cma_es_lib.py │ ├── ddpg.py │ ├── erwr.py │ ├── nop.py │ ├── npo.py │ ├── ppo.py │ ├── reps.py │ ├── tnpg.py │ ├── trpo.py │ ├── util.py │ └── vpg.py ├── baselines │ ├── __init__.py │ ├── base.py │ ├── gaussian_conv_baseline.py │ ├── gaussian_mlp_baseline.py │ ├── linear_feature_baseline.py │ └── zero_baseline.py ├── config.py ├── config_personal_template.py ├── core │ ├── __init__.py │ ├── lasagne_helpers.py │ ├── lasagne_layers.py │ ├── lasagne_powered.py │ ├── network.py │ ├── parameterized.py │ └── serializable.py ├── distributions │ ├── __init__.py │ ├── base.py │ ├── bernoulli.py │ ├── categorical.py │ ├── delta.py │ ├── diagonal_gaussian.py │ ├── recurrent_categorical.py │ └── recurrent_diagonal_gaussian.py ├── envs │ ├── __init__.py │ ├── base.py │ ├── box2d │ │ ├── __init__.py │ │ ├── box2d_env.py │ │ ├── box2d_viewer.py │ │ ├── car_parking_env.py │ │ ├── cartpole_env.py │ │ ├── cartpole_swingup_env.py │ │ ├── double_pendulum_env.py │ │ ├── models │ │ │ ├── car_parking.xml │ │ │ ├── car_parking.xml.rb │ │ │ ├── cartpole.xml.mako │ │ │ ├── double_pendulum.xml.mako │ │ │ └── mountain_car.xml.mako │ │ ├── mountain_car_env.py │ │ └── parser │ │ │ ├── __init__.py │ │ │ ├── xml_attr_types.py │ │ │ ├── xml_box2d.py │ │ │ └── xml_types.py │ ├── env_spec.py │ ├── grid_world_env.py │ ├── gym_env.py │ ├── identification_env.py │ ├── mujoco │ │ ├── __init__.py │ │ ├── ant_env.py │ │ ├── gather │ │ │ ├── __init__.py │ │ │ ├── ant_gather_env.py │ │ │ ├── embedded_viewer.py │ │ │ ├── gather_env.py │ │ │ ├── point_gather_env.py │ │ │ └── swimmer_gather_env.py │ │ ├── half_cheetah_env.py │ │ ├── hill │ │ │ ├── __init__.py │ │ │ ├── ant_hill_env.py │ │ │ ├── half_cheetah_hill_env.py │ │ │ ├── hill_env.py │ │ │ ├── hopper_hill_env.py │ │ │ ├── swimmer3d_hill_env.py │ │ │ ├── terrain.py │ │ │ └── walker2d_hill_env.py │ │ ├── hopper_env.py │ │ ├── humanoid_env.py │ │ ├── inverted_double_pendulum_env.py │ │ ├── maze │ │ │ ├── __init__.py │ │ │ ├── ant_maze_env.py │ │ │ ├── maze_env.py │ │ │ ├── maze_env_utils.py │ │ │ ├── point_maze_env.py │ │ │ └── swimmer_maze_env.py │ │ ├── mujoco_env.py │ │ ├── point_env.py │ │ ├── simple_humanoid_env.py │ │ ├── swimmer3d_env.py │ │ ├── swimmer_env.py │ │ └── walker2d_env.py │ ├── noisy_env.py │ ├── normalized_env.py │ ├── occlusion_env.py │ ├── proxy_env.py │ └── sliding_mem_env.py ├── exploration_strategies │ ├── __init__.py │ ├── base.py │ ├── gaussian_strategy.py │ └── ou_strategy.py ├── misc │ ├── __init__.py │ ├── autoargs.py │ ├── console.py │ ├── ext.py │ ├── instrument.py │ ├── krylov.py │ ├── logger.py │ ├── mako_utils.py │ ├── meta.py │ ├── nb_utils.py │ ├── overrides.py │ ├── resolve.py │ ├── special.py │ ├── tabulate.py │ ├── tensor_utils.py │ └── viewer2d.py ├── mujoco_py │ ├── .rvmrc │ ├── Gemfile │ ├── Gemfile.lock │ ├── __init__.py │ ├── codegen.rb │ ├── gen_binding.sh │ ├── glfw.py │ ├── mjconstants.py │ ├── mjcore.py │ ├── mjextra.py │ ├── mjlib.py │ ├── mjtypes.py │ ├── mjviewer.py │ └── util.py ├── optimizers │ ├── __init__.py │ ├── conjugate_gradient_optimizer.py │ ├── first_order_optimizer.py │ ├── hessian_free_optimizer.py │ ├── hf.py │ ├── lbfgs_optimizer.py │ ├── minibatch_dataset.py │ └── penalty_lbfgs_optimizer.py ├── plotter │ ├── __init__.py │ └── plotter.py ├── policies │ ├── __init__.py │ ├── base.py │ ├── categorical_conv_policy.py │ ├── categorical_gru_policy.py │ ├── categorical_mlp_policy.py │ ├── deterministic_mlp_policy.py │ ├── gaussian_gru_policy.py │ ├── gaussian_mlp_policy.py │ └── uniform_control_policy.py ├── q_functions │ ├── __init__.py │ ├── base.py │ └── continuous_mlp_q_function.py ├── regressors │ ├── __init__.py │ ├── categorical_mlp_regressor.py │ ├── gaussian_conv_regressor.py │ ├── gaussian_mlp_regressor.py │ └── product_regressor.py ├── sampler │ ├── __init__.py │ ├── base.py │ ├── parallel_sampler.py │ ├── stateful_pool.py │ └── utils.py ├── spaces │ ├── __init__.py │ ├── base.py │ ├── box.py │ ├── discrete.py │ └── product.py └── viskit │ ├── __init__.py │ ├── core.py │ ├── frontend.py │ ├── static │ ├── css │ │ ├── bootstrap.min.css │ │ └── dropdowns-enhancement.css │ └── js │ │ ├── bootstrap.min.js │ │ ├── dropdowns-enhancement.js │ │ ├── jquery-1.10.2.min.js │ │ ├── jquery.loadTemplate-1.5.6.js │ │ └── plotly-latest.min.js │ └── templates │ └── main.html ├── sandbox ├── Surprise_experiment.py ├── __init__.py ├── rocky │ ├── __init__.py │ └── tf │ │ ├── __init__.py │ │ ├── algos │ │ ├── __init__.py │ │ ├── batch_polopt.py │ │ ├── npg.py │ │ ├── npo.py │ │ ├── pg_svrg.py │ │ ├── robust_pg.py │ │ ├── trpo.py │ │ └── vpg.py │ │ ├── core │ │ ├── __init__.py │ │ ├── layers.py │ │ ├── layers_powered.py │ │ ├── network.py │ │ └── parameterized.py │ │ ├── distributions │ │ ├── __init__.py │ │ ├── base.py │ │ ├── bernoulli.py │ │ ├── categorical.py │ │ ├── diagonal_gaussian.py │ │ ├── recurrent_categorical.py │ │ └── recurrent_diagonal_gaussian.py │ │ ├── envs │ │ ├── __init__.py │ │ ├── base.py │ │ ├── parallel_vec_env_executor.py │ │ └── vec_env_executor.py │ │ ├── launchers │ │ ├── __init__.py │ │ ├── benchmark_svrg.py │ │ ├── benchmark_svrg_render.py │ │ ├── nohup.out │ │ ├── plotComparison.py │ │ ├── plotcurve.py │ │ ├── robust_DoublePendulum.py │ │ ├── run_svrg_ant.py │ │ ├── run_svrg_cheetah.py │ │ ├── run_svrg_hopper.py │ │ ├── run_svrg_swim.py │ │ ├── run_svrg_swim_lz.py │ │ ├── run_svrg_swim_render.py │ │ ├── run_svrg_swim_render_x.py │ │ ├── run_svrg_walker.py │ │ ├── run_svrg_walker_render.py │ │ ├── stein_trpo_swimmer.py │ │ ├── svrg_DoublePendulum.py │ │ ├── swim.png │ │ ├── trpo_cartpole.py │ │ ├── trpo_cartpole_recurrent.py │ │ ├── trpo_cartpole_render.py │ │ ├── trpo_gym_swimmer.py │ │ ├── trpo_gym_walker.py │ │ └── vpg_cartpole.py │ │ ├── misc │ │ ├── __init__.py │ │ └── tensor_utils.py │ │ ├── optimizers │ │ ├── __init__.py │ │ ├── conjugate_gradient_optimizer.py │ │ ├── first_order_optimizer.py │ │ ├── lbfgs_optimizer.py │ │ ├── penalty_lbfgs_optimizer.py │ │ ├── robust_opt.py │ │ ├── robust_trpo.py │ │ └── svrg.py │ │ ├── policies │ │ ├── __init__.py │ │ ├── base.py │ │ ├── categorical_conv_policy.py │ │ ├── categorical_gru_policy.py │ │ ├── categorical_lstm_policy.py │ │ ├── categorical_mlp_policy.py │ │ ├── deterministic_mlp_policy.py │ │ ├── gaussian_gru_policy.py │ │ ├── gaussian_lstm_policy.py │ │ ├── gaussian_mlp_policy.py │ │ └── uniform_control_policy.py │ │ ├── q_functions │ │ ├── __init__.py │ │ ├── base.py │ │ └── continuous_mlp_q_function.py │ │ ├── regressors │ │ ├── __init__.py │ │ ├── bernoulli_mlp_regressor.py │ │ ├── categorical_mlp_regressor.py │ │ ├── deterministic_mlp_regressor.py │ │ └── gaussian_mlp_regressor.py │ │ ├── samplers │ │ ├── __init__.py │ │ ├── batch_sampler.py │ │ └── vectorized_sampler.py │ │ └── spaces │ │ ├── __init__.py │ │ ├── box.py │ │ ├── discrete.py │ │ └── product.py ├── surprisebased │ ├── algos │ │ ├── __init__.py │ │ └── plus │ │ │ ├── __init__.py │ │ │ ├── erwr_plus.py │ │ │ ├── policy_gradient_plus.py │ │ │ ├── ppo_plus.py │ │ │ ├── sampler_plus.py │ │ │ ├── tnpg_plus.py │ │ │ ├── trpo_plus.py │ │ │ └── vpg_plus.py │ ├── envs │ │ ├── __init__.py │ │ ├── cartpole_swingup_env_x.py │ │ ├── half_cheetah_env_x.py │ │ ├── mountain_car_env_x.py │ │ ├── normalized_atari_env.py │ │ └── swimmer_env_x.py │ ├── exploration_bonuses │ │ ├── __init__.py │ │ ├── approx_kl_div_n_step_bonus.py │ │ ├── base.py │ │ ├── no_bonus.py │ │ ├── prediction_error_bonus.py │ │ └── surprisal_bonus.py │ └── regressors │ │ ├── __init__.py │ │ └── regularized_gaussian_mlp_regressor.py └── vime │ ├── envs │ └── double_pendulum_env_x1.py │ └── experiments │ └── run_sparse_trpo.py ├── scripts ├── __init__.py ├── plotcurve.py ├── resume_training.py ├── run_experiment_lite.py ├── setup_ec2_for_rllab.py ├── setup_linux.sh ├── setup_mujoco.sh ├── setup_osx.sh ├── sim_env.py ├── sim_policy.py ├── stein.11.3.png ├── stein_trpo.11.2.png ├── submit_gym.py └── sync_s3.py ├── setup.py ├── start.sh └── tests ├── __init__.py ├── algos ├── __init__.py └── test_trpo.py ├── envs ├── __init__.py ├── test_envs.py └── test_maze_env.py ├── regression_tests ├── __init__.py └── test_issue_3.py ├── test_algos.py ├── test_baselines.py ├── test_instrument.py ├── test_networks.py ├── test_sampler.py ├── test_serializable.py ├── test_spaces.py └── test_stateful_pool.py /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/.gitignore -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/README.md -------------------------------------------------------------------------------- /docs/Makefile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/Makefile -------------------------------------------------------------------------------- /docs/conf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/conf.py -------------------------------------------------------------------------------- /docs/index.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/index.rst -------------------------------------------------------------------------------- /docs/user/cluster.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/cluster.rst -------------------------------------------------------------------------------- /docs/user/cluster_1.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/cluster_1.png -------------------------------------------------------------------------------- /docs/user/cluster_2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/cluster_2.png -------------------------------------------------------------------------------- /docs/user/cluster_3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/cluster_3.png -------------------------------------------------------------------------------- /docs/user/experiments.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/experiments.rst -------------------------------------------------------------------------------- /docs/user/gym_integration.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/gym_integration.rst -------------------------------------------------------------------------------- /docs/user/implement_algo_advanced.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/implement_algo_advanced.rst -------------------------------------------------------------------------------- /docs/user/implement_algo_basic.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/implement_algo_basic.rst -------------------------------------------------------------------------------- /docs/user/implement_env.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/implement_env.rst -------------------------------------------------------------------------------- /docs/user/installation.rst: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/docs/user/installation.rst -------------------------------------------------------------------------------- /environment.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/environment.yml -------------------------------------------------------------------------------- /examples/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /examples/cluster_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/cluster_demo.py -------------------------------------------------------------------------------- /examples/cluster_gym_mujoco_demo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/cluster_gym_mujoco_demo.py -------------------------------------------------------------------------------- /examples/ddpg_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/ddpg_cartpole.py -------------------------------------------------------------------------------- /examples/nop_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/nop_cartpole.py -------------------------------------------------------------------------------- /examples/point_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/point_env.py -------------------------------------------------------------------------------- /examples/trpo_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/trpo_cartpole.py -------------------------------------------------------------------------------- /examples/trpo_cartpole_pickled.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/trpo_cartpole_pickled.py -------------------------------------------------------------------------------- /examples/trpo_cartpole_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/trpo_cartpole_recurrent.py -------------------------------------------------------------------------------- /examples/trpo_gym_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/trpo_gym_cartpole.py -------------------------------------------------------------------------------- /examples/trpo_gym_pendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/trpo_gym_pendulum.py -------------------------------------------------------------------------------- /examples/trpo_gym_tf_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/trpo_gym_tf_cartpole.py -------------------------------------------------------------------------------- /examples/trpo_point.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/trpo_point.py -------------------------------------------------------------------------------- /examples/trpo_swimmer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/trpo_swimmer.py -------------------------------------------------------------------------------- /examples/vpg_1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/vpg_1.py -------------------------------------------------------------------------------- /examples/vpg_2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/examples/vpg_2.py -------------------------------------------------------------------------------- /rllab/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/algos/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/algos/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/base.py -------------------------------------------------------------------------------- /rllab/algos/batch_polopt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/batch_polopt.py -------------------------------------------------------------------------------- /rllab/algos/cem.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/cem.py -------------------------------------------------------------------------------- /rllab/algos/cma_es.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/cma_es.py -------------------------------------------------------------------------------- /rllab/algos/cma_es_lib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/cma_es_lib.py -------------------------------------------------------------------------------- /rllab/algos/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/ddpg.py -------------------------------------------------------------------------------- /rllab/algos/erwr.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/erwr.py -------------------------------------------------------------------------------- /rllab/algos/nop.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/nop.py -------------------------------------------------------------------------------- /rllab/algos/npo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/npo.py -------------------------------------------------------------------------------- /rllab/algos/ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/ppo.py -------------------------------------------------------------------------------- /rllab/algos/reps.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/reps.py -------------------------------------------------------------------------------- /rllab/algos/tnpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/tnpg.py -------------------------------------------------------------------------------- /rllab/algos/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/trpo.py -------------------------------------------------------------------------------- /rllab/algos/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/util.py -------------------------------------------------------------------------------- /rllab/algos/vpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/algos/vpg.py -------------------------------------------------------------------------------- /rllab/baselines/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/baselines/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/baselines/base.py -------------------------------------------------------------------------------- /rllab/baselines/gaussian_conv_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/baselines/gaussian_conv_baseline.py -------------------------------------------------------------------------------- /rllab/baselines/gaussian_mlp_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/baselines/gaussian_mlp_baseline.py -------------------------------------------------------------------------------- /rllab/baselines/linear_feature_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/baselines/linear_feature_baseline.py -------------------------------------------------------------------------------- /rllab/baselines/zero_baseline.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/baselines/zero_baseline.py -------------------------------------------------------------------------------- /rllab/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/config.py -------------------------------------------------------------------------------- /rllab/config_personal_template.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/config_personal_template.py -------------------------------------------------------------------------------- /rllab/core/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/core/lasagne_helpers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/core/lasagne_helpers.py -------------------------------------------------------------------------------- /rllab/core/lasagne_layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/core/lasagne_layers.py -------------------------------------------------------------------------------- /rllab/core/lasagne_powered.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/core/lasagne_powered.py -------------------------------------------------------------------------------- /rllab/core/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/core/network.py -------------------------------------------------------------------------------- /rllab/core/parameterized.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/core/parameterized.py -------------------------------------------------------------------------------- /rllab/core/serializable.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/core/serializable.py -------------------------------------------------------------------------------- /rllab/distributions/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/distributions/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/distributions/base.py -------------------------------------------------------------------------------- /rllab/distributions/bernoulli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/distributions/bernoulli.py -------------------------------------------------------------------------------- /rllab/distributions/categorical.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/distributions/categorical.py -------------------------------------------------------------------------------- /rllab/distributions/delta.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/distributions/delta.py -------------------------------------------------------------------------------- /rllab/distributions/diagonal_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/distributions/diagonal_gaussian.py -------------------------------------------------------------------------------- /rllab/distributions/recurrent_categorical.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/distributions/recurrent_categorical.py -------------------------------------------------------------------------------- /rllab/distributions/recurrent_diagonal_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/distributions/recurrent_diagonal_gaussian.py -------------------------------------------------------------------------------- /rllab/envs/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/envs/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/base.py -------------------------------------------------------------------------------- /rllab/envs/box2d/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/envs/box2d/box2d_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/box2d_env.py -------------------------------------------------------------------------------- /rllab/envs/box2d/box2d_viewer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/box2d_viewer.py -------------------------------------------------------------------------------- /rllab/envs/box2d/car_parking_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/car_parking_env.py -------------------------------------------------------------------------------- /rllab/envs/box2d/cartpole_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/cartpole_env.py -------------------------------------------------------------------------------- /rllab/envs/box2d/cartpole_swingup_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/cartpole_swingup_env.py -------------------------------------------------------------------------------- /rllab/envs/box2d/double_pendulum_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/double_pendulum_env.py -------------------------------------------------------------------------------- /rllab/envs/box2d/models/car_parking.xml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/models/car_parking.xml -------------------------------------------------------------------------------- /rllab/envs/box2d/models/car_parking.xml.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/models/car_parking.xml.rb -------------------------------------------------------------------------------- /rllab/envs/box2d/models/cartpole.xml.mako: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/models/cartpole.xml.mako -------------------------------------------------------------------------------- /rllab/envs/box2d/models/double_pendulum.xml.mako: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/models/double_pendulum.xml.mako -------------------------------------------------------------------------------- /rllab/envs/box2d/models/mountain_car.xml.mako: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/models/mountain_car.xml.mako -------------------------------------------------------------------------------- /rllab/envs/box2d/mountain_car_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/mountain_car_env.py -------------------------------------------------------------------------------- /rllab/envs/box2d/parser/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/parser/__init__.py -------------------------------------------------------------------------------- /rllab/envs/box2d/parser/xml_attr_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/parser/xml_attr_types.py -------------------------------------------------------------------------------- /rllab/envs/box2d/parser/xml_box2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/parser/xml_box2d.py -------------------------------------------------------------------------------- /rllab/envs/box2d/parser/xml_types.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/box2d/parser/xml_types.py -------------------------------------------------------------------------------- /rllab/envs/env_spec.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/env_spec.py -------------------------------------------------------------------------------- /rllab/envs/grid_world_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/grid_world_env.py -------------------------------------------------------------------------------- /rllab/envs/gym_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/gym_env.py -------------------------------------------------------------------------------- /rllab/envs/identification_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/identification_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/envs/mujoco/ant_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/ant_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/gather/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/envs/mujoco/gather/ant_gather_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/gather/ant_gather_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/gather/embedded_viewer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/gather/embedded_viewer.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/gather/gather_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/gather/gather_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/gather/point_gather_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/gather/point_gather_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/gather/swimmer_gather_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/gather/swimmer_gather_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/half_cheetah_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/half_cheetah_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/hill/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/envs/mujoco/hill/ant_hill_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/hill/ant_hill_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/hill/half_cheetah_hill_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/hill/half_cheetah_hill_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/hill/hill_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/hill/hill_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/hill/hopper_hill_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/hill/hopper_hill_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/hill/swimmer3d_hill_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/hill/swimmer3d_hill_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/hill/terrain.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/hill/terrain.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/hill/walker2d_hill_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/hill/walker2d_hill_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/hopper_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/hopper_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/humanoid_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/humanoid_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/inverted_double_pendulum_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/inverted_double_pendulum_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/maze/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/envs/mujoco/maze/ant_maze_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/maze/ant_maze_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/maze/maze_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/maze/maze_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/maze/maze_env_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/maze/maze_env_utils.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/maze/point_maze_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/maze/point_maze_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/maze/swimmer_maze_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/maze/swimmer_maze_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/mujoco_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/mujoco_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/point_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/point_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/simple_humanoid_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/simple_humanoid_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/swimmer3d_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/swimmer3d_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/swimmer_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/swimmer_env.py -------------------------------------------------------------------------------- /rllab/envs/mujoco/walker2d_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/mujoco/walker2d_env.py -------------------------------------------------------------------------------- /rllab/envs/noisy_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/noisy_env.py -------------------------------------------------------------------------------- /rllab/envs/normalized_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/normalized_env.py -------------------------------------------------------------------------------- /rllab/envs/occlusion_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/occlusion_env.py -------------------------------------------------------------------------------- /rllab/envs/proxy_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/proxy_env.py -------------------------------------------------------------------------------- /rllab/envs/sliding_mem_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/envs/sliding_mem_env.py -------------------------------------------------------------------------------- /rllab/exploration_strategies/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/exploration_strategies/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/exploration_strategies/base.py -------------------------------------------------------------------------------- /rllab/exploration_strategies/gaussian_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/exploration_strategies/gaussian_strategy.py -------------------------------------------------------------------------------- /rllab/exploration_strategies/ou_strategy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/exploration_strategies/ou_strategy.py -------------------------------------------------------------------------------- /rllab/misc/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/misc/autoargs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/autoargs.py -------------------------------------------------------------------------------- /rllab/misc/console.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/console.py -------------------------------------------------------------------------------- /rllab/misc/ext.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/ext.py -------------------------------------------------------------------------------- /rllab/misc/instrument.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/instrument.py -------------------------------------------------------------------------------- /rllab/misc/krylov.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/krylov.py -------------------------------------------------------------------------------- /rllab/misc/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/logger.py -------------------------------------------------------------------------------- /rllab/misc/mako_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/mako_utils.py -------------------------------------------------------------------------------- /rllab/misc/meta.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/misc/nb_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/nb_utils.py -------------------------------------------------------------------------------- /rllab/misc/overrides.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/overrides.py -------------------------------------------------------------------------------- /rllab/misc/resolve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/resolve.py -------------------------------------------------------------------------------- /rllab/misc/special.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/special.py -------------------------------------------------------------------------------- /rllab/misc/tabulate.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/tabulate.py -------------------------------------------------------------------------------- /rllab/misc/tensor_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/tensor_utils.py -------------------------------------------------------------------------------- /rllab/misc/viewer2d.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/misc/viewer2d.py -------------------------------------------------------------------------------- /rllab/mujoco_py/.rvmrc: -------------------------------------------------------------------------------- 1 | rvm use 2.1.0@mjpy --create 2 | -------------------------------------------------------------------------------- /rllab/mujoco_py/Gemfile: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/Gemfile -------------------------------------------------------------------------------- /rllab/mujoco_py/Gemfile.lock: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/Gemfile.lock -------------------------------------------------------------------------------- /rllab/mujoco_py/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/__init__.py -------------------------------------------------------------------------------- /rllab/mujoco_py/codegen.rb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/codegen.rb -------------------------------------------------------------------------------- /rllab/mujoco_py/gen_binding.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/gen_binding.sh -------------------------------------------------------------------------------- /rllab/mujoco_py/glfw.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/glfw.py -------------------------------------------------------------------------------- /rllab/mujoco_py/mjconstants.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/mjconstants.py -------------------------------------------------------------------------------- /rllab/mujoco_py/mjcore.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/mjcore.py -------------------------------------------------------------------------------- /rllab/mujoco_py/mjextra.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/mjextra.py -------------------------------------------------------------------------------- /rllab/mujoco_py/mjlib.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/mjlib.py -------------------------------------------------------------------------------- /rllab/mujoco_py/mjtypes.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/mjtypes.py -------------------------------------------------------------------------------- /rllab/mujoco_py/mjviewer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/mjviewer.py -------------------------------------------------------------------------------- /rllab/mujoco_py/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/mujoco_py/util.py -------------------------------------------------------------------------------- /rllab/optimizers/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/optimizers/conjugate_gradient_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/optimizers/conjugate_gradient_optimizer.py -------------------------------------------------------------------------------- /rllab/optimizers/first_order_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/optimizers/first_order_optimizer.py -------------------------------------------------------------------------------- /rllab/optimizers/hessian_free_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/optimizers/hessian_free_optimizer.py -------------------------------------------------------------------------------- /rllab/optimizers/hf.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/optimizers/hf.py -------------------------------------------------------------------------------- /rllab/optimizers/lbfgs_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/optimizers/lbfgs_optimizer.py -------------------------------------------------------------------------------- /rllab/optimizers/minibatch_dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/optimizers/minibatch_dataset.py -------------------------------------------------------------------------------- /rllab/optimizers/penalty_lbfgs_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/optimizers/penalty_lbfgs_optimizer.py -------------------------------------------------------------------------------- /rllab/plotter/__init__.py: -------------------------------------------------------------------------------- 1 | from .plotter import * 2 | -------------------------------------------------------------------------------- /rllab/plotter/plotter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/plotter/plotter.py -------------------------------------------------------------------------------- /rllab/policies/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/policies/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/policies/base.py -------------------------------------------------------------------------------- /rllab/policies/categorical_conv_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/policies/categorical_conv_policy.py -------------------------------------------------------------------------------- /rllab/policies/categorical_gru_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/policies/categorical_gru_policy.py -------------------------------------------------------------------------------- /rllab/policies/categorical_mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/policies/categorical_mlp_policy.py -------------------------------------------------------------------------------- /rllab/policies/deterministic_mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/policies/deterministic_mlp_policy.py -------------------------------------------------------------------------------- /rllab/policies/gaussian_gru_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/policies/gaussian_gru_policy.py -------------------------------------------------------------------------------- /rllab/policies/gaussian_mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/policies/gaussian_mlp_policy.py -------------------------------------------------------------------------------- /rllab/policies/uniform_control_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/policies/uniform_control_policy.py -------------------------------------------------------------------------------- /rllab/q_functions/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/q_functions/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/q_functions/base.py -------------------------------------------------------------------------------- /rllab/q_functions/continuous_mlp_q_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/q_functions/continuous_mlp_q_function.py -------------------------------------------------------------------------------- /rllab/regressors/__init__.py: -------------------------------------------------------------------------------- 1 | __author__ = 'dementrock' 2 | -------------------------------------------------------------------------------- /rllab/regressors/categorical_mlp_regressor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/regressors/categorical_mlp_regressor.py -------------------------------------------------------------------------------- /rllab/regressors/gaussian_conv_regressor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/regressors/gaussian_conv_regressor.py -------------------------------------------------------------------------------- /rllab/regressors/gaussian_mlp_regressor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/regressors/gaussian_mlp_regressor.py -------------------------------------------------------------------------------- /rllab/regressors/product_regressor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/regressors/product_regressor.py -------------------------------------------------------------------------------- /rllab/sampler/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /rllab/sampler/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/sampler/base.py -------------------------------------------------------------------------------- /rllab/sampler/parallel_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/sampler/parallel_sampler.py -------------------------------------------------------------------------------- /rllab/sampler/stateful_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/sampler/stateful_pool.py -------------------------------------------------------------------------------- /rllab/sampler/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/sampler/utils.py -------------------------------------------------------------------------------- /rllab/spaces/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/spaces/__init__.py -------------------------------------------------------------------------------- /rllab/spaces/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/spaces/base.py -------------------------------------------------------------------------------- /rllab/spaces/box.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/spaces/box.py -------------------------------------------------------------------------------- /rllab/spaces/discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/spaces/discrete.py -------------------------------------------------------------------------------- /rllab/spaces/product.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/spaces/product.py -------------------------------------------------------------------------------- /rllab/viskit/__init__.py: -------------------------------------------------------------------------------- 1 | __author__ = 'dementrock' 2 | -------------------------------------------------------------------------------- /rllab/viskit/core.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/core.py -------------------------------------------------------------------------------- /rllab/viskit/frontend.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/frontend.py -------------------------------------------------------------------------------- /rllab/viskit/static/css/bootstrap.min.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/static/css/bootstrap.min.css -------------------------------------------------------------------------------- /rllab/viskit/static/css/dropdowns-enhancement.css: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/static/css/dropdowns-enhancement.css -------------------------------------------------------------------------------- /rllab/viskit/static/js/bootstrap.min.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/static/js/bootstrap.min.js -------------------------------------------------------------------------------- /rllab/viskit/static/js/dropdowns-enhancement.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/static/js/dropdowns-enhancement.js -------------------------------------------------------------------------------- /rllab/viskit/static/js/jquery-1.10.2.min.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/static/js/jquery-1.10.2.min.js -------------------------------------------------------------------------------- /rllab/viskit/static/js/jquery.loadTemplate-1.5.6.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/static/js/jquery.loadTemplate-1.5.6.js -------------------------------------------------------------------------------- /rllab/viskit/static/js/plotly-latest.min.js: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/static/js/plotly-latest.min.js -------------------------------------------------------------------------------- /rllab/viskit/templates/main.html: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/rllab/viskit/templates/main.html -------------------------------------------------------------------------------- /sandbox/Surprise_experiment.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/Surprise_experiment.py -------------------------------------------------------------------------------- /sandbox/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sandbox/rocky/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/algos/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/algos/batch_polopt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/algos/batch_polopt.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/algos/npg.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/algos/npo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/algos/npo.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/algos/pg_svrg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/algos/pg_svrg.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/algos/robust_pg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/algos/robust_pg.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/algos/trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/algos/trpo.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/algos/vpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/algos/vpg.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/core/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/core/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/core/layers.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/core/layers_powered.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/core/layers_powered.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/core/network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/core/network.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/core/parameterized.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/core/parameterized.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/distributions/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/distributions/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/distributions/base.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/distributions/bernoulli.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/distributions/bernoulli.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/distributions/categorical.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/distributions/categorical.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/distributions/diagonal_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/distributions/diagonal_gaussian.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/distributions/recurrent_categorical.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/distributions/recurrent_categorical.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/distributions/recurrent_diagonal_gaussian.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/distributions/recurrent_diagonal_gaussian.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/envs/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/envs/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/envs/base.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/envs/parallel_vec_env_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/envs/parallel_vec_env_executor.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/envs/vec_env_executor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/envs/vec_env_executor.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/benchmark_svrg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/benchmark_svrg.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/benchmark_svrg_render.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/benchmark_svrg_render.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/nohup.out: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/nohup.out -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/plotComparison.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/plotComparison.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/plotcurve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/plotcurve.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/robust_DoublePendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/robust_DoublePendulum.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/run_svrg_ant.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/run_svrg_ant.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/run_svrg_cheetah.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/run_svrg_cheetah.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/run_svrg_hopper.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/run_svrg_hopper.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/run_svrg_swim.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/run_svrg_swim.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/run_svrg_swim_lz.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/run_svrg_swim_lz.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/run_svrg_swim_render.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/run_svrg_swim_render.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/run_svrg_swim_render_x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/run_svrg_swim_render_x.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/run_svrg_walker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/run_svrg_walker.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/run_svrg_walker_render.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/run_svrg_walker_render.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/stein_trpo_swimmer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/stein_trpo_swimmer.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/svrg_DoublePendulum.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/svrg_DoublePendulum.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/swim.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/swim.png -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/trpo_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/trpo_cartpole.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/trpo_cartpole_recurrent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/trpo_cartpole_recurrent.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/trpo_cartpole_render.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/trpo_cartpole_render.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/trpo_gym_swimmer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/trpo_gym_swimmer.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/trpo_gym_walker.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/trpo_gym_walker.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/launchers/vpg_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/launchers/vpg_cartpole.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/misc/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/misc/tensor_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/misc/tensor_utils.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/optimizers/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/optimizers/conjugate_gradient_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/optimizers/conjugate_gradient_optimizer.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/optimizers/first_order_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/optimizers/first_order_optimizer.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/optimizers/lbfgs_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/optimizers/lbfgs_optimizer.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/optimizers/penalty_lbfgs_optimizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/optimizers/penalty_lbfgs_optimizer.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/optimizers/robust_opt.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/optimizers/robust_opt.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/optimizers/robust_trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/optimizers/robust_trpo.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/optimizers/svrg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/optimizers/svrg.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/base.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/categorical_conv_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/categorical_conv_policy.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/categorical_gru_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/categorical_gru_policy.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/categorical_lstm_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/categorical_lstm_policy.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/categorical_mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/categorical_mlp_policy.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/deterministic_mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/deterministic_mlp_policy.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/gaussian_gru_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/gaussian_gru_policy.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/gaussian_lstm_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/gaussian_lstm_policy.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/gaussian_mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/gaussian_mlp_policy.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/policies/uniform_control_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/policies/uniform_control_policy.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/q_functions/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/q_functions/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/q_functions/base.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/q_functions/continuous_mlp_q_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/q_functions/continuous_mlp_q_function.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/regressors/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/regressors/bernoulli_mlp_regressor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/regressors/bernoulli_mlp_regressor.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/regressors/categorical_mlp_regressor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/regressors/categorical_mlp_regressor.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/regressors/deterministic_mlp_regressor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/regressors/deterministic_mlp_regressor.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/regressors/gaussian_mlp_regressor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/regressors/gaussian_mlp_regressor.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/samplers/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /sandbox/rocky/tf/samplers/batch_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/samplers/batch_sampler.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/samplers/vectorized_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/samplers/vectorized_sampler.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/spaces/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/spaces/__init__.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/spaces/box.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/spaces/box.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/spaces/discrete.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/spaces/discrete.py -------------------------------------------------------------------------------- /sandbox/rocky/tf/spaces/product.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/rocky/tf/spaces/product.py -------------------------------------------------------------------------------- /sandbox/surprisebased/algos/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sandbox/surprisebased/algos/plus/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sandbox/surprisebased/algos/plus/erwr_plus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/algos/plus/erwr_plus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/algos/plus/policy_gradient_plus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/algos/plus/policy_gradient_plus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/algos/plus/ppo_plus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/algos/plus/ppo_plus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/algos/plus/sampler_plus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/algos/plus/sampler_plus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/algos/plus/tnpg_plus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/algos/plus/tnpg_plus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/algos/plus/trpo_plus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/algos/plus/trpo_plus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/algos/plus/vpg_plus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/algos/plus/vpg_plus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/envs/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sandbox/surprisebased/envs/cartpole_swingup_env_x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/envs/cartpole_swingup_env_x.py -------------------------------------------------------------------------------- /sandbox/surprisebased/envs/half_cheetah_env_x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/envs/half_cheetah_env_x.py -------------------------------------------------------------------------------- /sandbox/surprisebased/envs/mountain_car_env_x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/envs/mountain_car_env_x.py -------------------------------------------------------------------------------- /sandbox/surprisebased/envs/normalized_atari_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/envs/normalized_atari_env.py -------------------------------------------------------------------------------- /sandbox/surprisebased/envs/swimmer_env_x.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/envs/swimmer_env_x.py -------------------------------------------------------------------------------- /sandbox/surprisebased/exploration_bonuses/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sandbox/surprisebased/exploration_bonuses/approx_kl_div_n_step_bonus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/exploration_bonuses/approx_kl_div_n_step_bonus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/exploration_bonuses/base.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/exploration_bonuses/base.py -------------------------------------------------------------------------------- /sandbox/surprisebased/exploration_bonuses/no_bonus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/exploration_bonuses/no_bonus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/exploration_bonuses/prediction_error_bonus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/exploration_bonuses/prediction_error_bonus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/exploration_bonuses/surprisal_bonus.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/exploration_bonuses/surprisal_bonus.py -------------------------------------------------------------------------------- /sandbox/surprisebased/regressors/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /sandbox/surprisebased/regressors/regularized_gaussian_mlp_regressor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/surprisebased/regressors/regularized_gaussian_mlp_regressor.py -------------------------------------------------------------------------------- /sandbox/vime/envs/double_pendulum_env_x1.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/vime/envs/double_pendulum_env_x1.py -------------------------------------------------------------------------------- /sandbox/vime/experiments/run_sparse_trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/sandbox/vime/experiments/run_sparse_trpo.py -------------------------------------------------------------------------------- /scripts/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /scripts/plotcurve.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/plotcurve.py -------------------------------------------------------------------------------- /scripts/resume_training.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/resume_training.py -------------------------------------------------------------------------------- /scripts/run_experiment_lite.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/run_experiment_lite.py -------------------------------------------------------------------------------- /scripts/setup_ec2_for_rllab.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/setup_ec2_for_rllab.py -------------------------------------------------------------------------------- /scripts/setup_linux.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/setup_linux.sh -------------------------------------------------------------------------------- /scripts/setup_mujoco.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/setup_mujoco.sh -------------------------------------------------------------------------------- /scripts/setup_osx.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/setup_osx.sh -------------------------------------------------------------------------------- /scripts/sim_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/sim_env.py -------------------------------------------------------------------------------- /scripts/sim_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/sim_policy.py -------------------------------------------------------------------------------- /scripts/stein.11.3.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/stein.11.3.png -------------------------------------------------------------------------------- /scripts/stein_trpo.11.2.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/stein_trpo.11.2.png -------------------------------------------------------------------------------- /scripts/submit_gym.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/submit_gym.py -------------------------------------------------------------------------------- /scripts/sync_s3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/scripts/sync_s3.py -------------------------------------------------------------------------------- /setup.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/setup.py -------------------------------------------------------------------------------- /start.sh: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/start.sh -------------------------------------------------------------------------------- /tests/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/algos/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /tests/algos/test_trpo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/algos/test_trpo.py -------------------------------------------------------------------------------- /tests/envs/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /tests/envs/test_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/envs/test_envs.py -------------------------------------------------------------------------------- /tests/envs/test_maze_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/envs/test_maze_env.py -------------------------------------------------------------------------------- /tests/regression_tests/__init__.py: -------------------------------------------------------------------------------- 1 | 2 | -------------------------------------------------------------------------------- /tests/regression_tests/test_issue_3.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/regression_tests/test_issue_3.py -------------------------------------------------------------------------------- /tests/test_algos.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/test_algos.py -------------------------------------------------------------------------------- /tests/test_baselines.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/test_baselines.py -------------------------------------------------------------------------------- /tests/test_instrument.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/test_instrument.py -------------------------------------------------------------------------------- /tests/test_networks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/test_networks.py -------------------------------------------------------------------------------- /tests/test_sampler.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/test_sampler.py -------------------------------------------------------------------------------- /tests/test_serializable.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/test_serializable.py -------------------------------------------------------------------------------- /tests/test_spaces.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/test_spaces.py -------------------------------------------------------------------------------- /tests/test_stateful_pool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/tianbingsz/SVRG/HEAD/tests/test_stateful_pool.py --------------------------------------------------------------------------------