├── CODE_OF_CONDUCT.md ├── CONTRIBUTING.md ├── LICENSE ├── README.md ├── configs ├── algos │ ├── mb_trpo.yml │ ├── mf.yml │ └── slbo.yml ├── envs │ ├── ant.yml │ ├── half_cheetah.yml │ ├── half_cheetah_short.yml │ ├── hopper.yml │ ├── humanoid.yml │ ├── swimmer.yml │ └── walker.yml └── multi_step │ ├── 1.yml │ ├── 2.yml │ ├── 4.yml │ └── 8.yml ├── lunzi ├── Logger.py ├── __init__.py ├── config.py ├── dataset.py ├── nn │ ├── __init__.py │ ├── container.py │ ├── flat_param.py │ ├── layers.py │ ├── loss.py │ ├── module.py │ ├── parameter.py │ ├── patch.py │ └── utils.py ├── stubs.py └── stubs.pyi ├── main.py ├── requirements.txt ├── rllab_requirements.txt └── slbo ├── __init__.py ├── algos ├── TRPO.py └── __init__.py ├── dynamics_model.py ├── envs ├── __init__.py ├── batched_env.py ├── mujoco │ ├── __init__.py │ ├── ant_env.py │ ├── half_cheetah_env.py │ ├── hopper_env.py │ ├── humanoid_env.py │ ├── swimmer_env.py │ └── walker2d_env.py └── virtual_env.py ├── loss ├── __init__.py └── multi_step_loss.py ├── partial_envs.py ├── policies ├── __init__.py ├── gaussian_mlp_policy.py └── uniform_policy.py ├── q_function ├── __init__.py └── mlp_q_function.py ├── utils ├── OU_noise.py ├── __init__.py ├── average_meter.py ├── dataset.py ├── flags.py ├── initializer.py ├── multi_layer_perceptron.py ├── normalizer.py ├── np_utils.py ├── runner.py ├── tf_utils.py └── truncated_normal.py └── v_function ├── __init__.py └── mlp_v_function.py /CODE_OF_CONDUCT.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/CODE_OF_CONDUCT.md -------------------------------------------------------------------------------- /CONTRIBUTING.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/CONTRIBUTING.md -------------------------------------------------------------------------------- /LICENSE: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/LICENSE -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/README.md -------------------------------------------------------------------------------- /configs/algos/mb_trpo.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/algos/mb_trpo.yml -------------------------------------------------------------------------------- /configs/algos/mf.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/algos/mf.yml -------------------------------------------------------------------------------- /configs/algos/slbo.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/algos/slbo.yml -------------------------------------------------------------------------------- /configs/envs/ant.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/envs/ant.yml -------------------------------------------------------------------------------- /configs/envs/half_cheetah.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/envs/half_cheetah.yml -------------------------------------------------------------------------------- /configs/envs/half_cheetah_short.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/envs/half_cheetah_short.yml -------------------------------------------------------------------------------- /configs/envs/hopper.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/envs/hopper.yml -------------------------------------------------------------------------------- /configs/envs/humanoid.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/envs/humanoid.yml -------------------------------------------------------------------------------- /configs/envs/swimmer.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/envs/swimmer.yml -------------------------------------------------------------------------------- /configs/envs/walker.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/envs/walker.yml -------------------------------------------------------------------------------- /configs/multi_step/1.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/multi_step/1.yml -------------------------------------------------------------------------------- /configs/multi_step/2.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/multi_step/2.yml -------------------------------------------------------------------------------- /configs/multi_step/4.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/multi_step/4.yml -------------------------------------------------------------------------------- /configs/multi_step/8.yml: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/configs/multi_step/8.yml -------------------------------------------------------------------------------- /lunzi/Logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/Logger.py -------------------------------------------------------------------------------- /lunzi/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/__init__.py -------------------------------------------------------------------------------- /lunzi/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/config.py -------------------------------------------------------------------------------- /lunzi/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/dataset.py -------------------------------------------------------------------------------- /lunzi/nn/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/nn/__init__.py -------------------------------------------------------------------------------- /lunzi/nn/container.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/nn/container.py -------------------------------------------------------------------------------- /lunzi/nn/flat_param.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/nn/flat_param.py -------------------------------------------------------------------------------- /lunzi/nn/layers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/nn/layers.py -------------------------------------------------------------------------------- /lunzi/nn/loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/nn/loss.py -------------------------------------------------------------------------------- /lunzi/nn/module.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/nn/module.py -------------------------------------------------------------------------------- /lunzi/nn/parameter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/nn/parameter.py -------------------------------------------------------------------------------- /lunzi/nn/patch.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/nn/patch.py -------------------------------------------------------------------------------- /lunzi/nn/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/nn/utils.py -------------------------------------------------------------------------------- /lunzi/stubs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/stubs.py -------------------------------------------------------------------------------- /lunzi/stubs.pyi: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/lunzi/stubs.pyi -------------------------------------------------------------------------------- /main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/main.py -------------------------------------------------------------------------------- /requirements.txt: -------------------------------------------------------------------------------- 1 | tensorflow==1.9.0 2 | numpy 3 | pyyaml 4 | termcolor 5 | gym 6 | json_tricks 7 | -------------------------------------------------------------------------------- /rllab_requirements.txt: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/rllab_requirements.txt -------------------------------------------------------------------------------- /slbo/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /slbo/algos/TRPO.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/algos/TRPO.py -------------------------------------------------------------------------------- /slbo/algos/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /slbo/dynamics_model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/dynamics_model.py -------------------------------------------------------------------------------- /slbo/envs/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/envs/__init__.py -------------------------------------------------------------------------------- /slbo/envs/batched_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/envs/batched_env.py -------------------------------------------------------------------------------- /slbo/envs/mujoco/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /slbo/envs/mujoco/ant_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/envs/mujoco/ant_env.py -------------------------------------------------------------------------------- /slbo/envs/mujoco/half_cheetah_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/envs/mujoco/half_cheetah_env.py -------------------------------------------------------------------------------- /slbo/envs/mujoco/hopper_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/envs/mujoco/hopper_env.py -------------------------------------------------------------------------------- /slbo/envs/mujoco/humanoid_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/envs/mujoco/humanoid_env.py -------------------------------------------------------------------------------- /slbo/envs/mujoco/swimmer_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/envs/mujoco/swimmer_env.py -------------------------------------------------------------------------------- /slbo/envs/mujoco/walker2d_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/envs/mujoco/walker2d_env.py -------------------------------------------------------------------------------- /slbo/envs/virtual_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/envs/virtual_env.py -------------------------------------------------------------------------------- /slbo/loss/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /slbo/loss/multi_step_loss.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/loss/multi_step_loss.py -------------------------------------------------------------------------------- /slbo/partial_envs.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/partial_envs.py -------------------------------------------------------------------------------- /slbo/policies/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/policies/__init__.py -------------------------------------------------------------------------------- /slbo/policies/gaussian_mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/policies/gaussian_mlp_policy.py -------------------------------------------------------------------------------- /slbo/policies/uniform_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/policies/uniform_policy.py -------------------------------------------------------------------------------- /slbo/q_function/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/q_function/__init__.py -------------------------------------------------------------------------------- /slbo/q_function/mlp_q_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/q_function/mlp_q_function.py -------------------------------------------------------------------------------- /slbo/utils/OU_noise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/OU_noise.py -------------------------------------------------------------------------------- /slbo/utils/__init__.py: -------------------------------------------------------------------------------- 1 | # Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved. 2 | -------------------------------------------------------------------------------- /slbo/utils/average_meter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/average_meter.py -------------------------------------------------------------------------------- /slbo/utils/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/dataset.py -------------------------------------------------------------------------------- /slbo/utils/flags.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/flags.py -------------------------------------------------------------------------------- /slbo/utils/initializer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/initializer.py -------------------------------------------------------------------------------- /slbo/utils/multi_layer_perceptron.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/multi_layer_perceptron.py -------------------------------------------------------------------------------- /slbo/utils/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/normalizer.py -------------------------------------------------------------------------------- /slbo/utils/np_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/np_utils.py -------------------------------------------------------------------------------- /slbo/utils/runner.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/runner.py -------------------------------------------------------------------------------- /slbo/utils/tf_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/tf_utils.py -------------------------------------------------------------------------------- /slbo/utils/truncated_normal.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/utils/truncated_normal.py -------------------------------------------------------------------------------- /slbo/v_function/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/v_function/__init__.py -------------------------------------------------------------------------------- /slbo/v_function/mlp_v_function.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/roosephu/slbo/HEAD/slbo/v_function/mlp_v_function.py --------------------------------------------------------------------------------