├── .DS_Store ├── .gitignore ├── 1_sb_ppo_agent.py ├── 2_supermario_dqn.ipynb ├── 4_pong_dqn (1).ipynb ├── README.md └── stable_baselines ├── __init__.py ├── a2c ├── __init__.py ├── a2c.py ├── run_atari.py └── utils.py ├── acer ├── __init__.py ├── acer_simple.py ├── buffer.py └── run_atari.py ├── acktr ├── __init__.py ├── acktr_cont.py ├── acktr_disc.py ├── kfac.py ├── kfac_utils.py ├── policies.py ├── run_atari.py ├── run_mujoco.py ├── utils.py └── value_functions.py ├── bench ├── __init__.py ├── benchmarks.py └── monitor.py ├── common ├── __init__.py ├── atari_wrappers.py ├── base_class.py ├── cg.py ├── cmd_util.py ├── console_util.py ├── dataset.py ├── distributions.py ├── filters.py ├── identity_env.py ├── input.py ├── math_util.py ├── misc_util.py ├── mpi_adam.py ├── mpi_fork.py ├── mpi_moments.py ├── mpi_running_mean_std.py ├── policies.py ├── runners.py ├── running_mean_std.py ├── running_stat.py ├── schedules.py ├── segment_tree.py ├── tf_util.py ├── tile_images.py └── vec_env │ ├── __init__.py │ ├── base_vec_env.py │ ├── dummy_vec_env.py │ ├── subproc_vec_env.py │ ├── vec_frame_stack.py │ └── vec_normalize.py ├── ddpg ├── __init__.py ├── ddpg.py ├── main.py ├── memory.py ├── noise.py └── policies.py ├── deepq ├── __init__.py ├── build_graph.py ├── dqn.py ├── dqn_10_sb_dqn_supermari_decay_resolution_exploration.py ├── dqn_12_sb_dqn_supermari_decay_resolution_exploration_step_10.py ├── dqn_13_sb_dqn_supermari_decay_resolution_exploration_step_20_exploration_term_5000.py ├── dqn_14_resoultion_network.py ├── dqn_9_sb_dqn_supermari_resolution_exploration.py ├── experiments │ ├── __init__.py │ ├── custom_cartpole.py │ ├── enjoy_cartpole.py │ ├── enjoy_mountaincar.py │ ├── enjoy_pong.py │ ├── run_atari.py │ ├── train_cartpole.py │ └── train_mountaincar.py ├── policies.py ├── replay_buffer.py └── utils.py ├── gail ├── __init__.py ├── adversary.py ├── behavior_clone.py ├── dataset │ ├── __init__.py │ └── mujocodset.py ├── gail_eval.py ├── mlp_policy.py ├── model.py ├── result │ ├── HalfCheetah-normalized-deterministic-scores.png │ ├── HalfCheetah-normalized-stochastic-scores.png │ ├── HalfCheetah-unnormalized-deterministic-scores.png │ ├── HalfCheetah-unnormalized-stochastic-scores.png │ ├── Hopper-normalized-deterministic-scores.png │ ├── Hopper-normalized-stochastic-scores.png │ ├── Hopper-unnormalized-deterministic-scores.png │ ├── Hopper-unnormalized-stochastic-scores.png │ ├── Humanoid-normalized-deterministic-scores.png │ ├── Humanoid-normalized-stochastic-scores.png │ ├── Humanoid-unnormalized-deterministic-scores.png │ ├── Humanoid-unnormalized-stochastic-scores.png │ ├── HumanoidStandup-normalized-deterministic-scores.png │ ├── HumanoidStandup-normalized-stochastic-scores.png │ ├── HumanoidStandup-unnormalized-deterministic-scores.png │ ├── HumanoidStandup-unnormalized-stochastic-scores.png │ ├── Walker2d-normalized-deterministic-scores.png │ ├── Walker2d-normalized-stochastic-scores.png │ ├── Walker2d-unnormalized-deterministic-scores.png │ ├── Walker2d-unnormalized-stochastic-scores.png │ ├── gail-result.md │ ├── halfcheetah-training.png │ ├── hopper-training.png │ ├── humanoid-training.png │ ├── humanoidstandup-training.png │ └── walker2d-training.png ├── run_mujoco.py └── statistics.py ├── her ├── __init__.py ├── actor_critic.py ├── ddpg.py ├── experiment │ ├── __init__.py │ ├── config.py │ ├── play.py │ ├── plot.py │ └── train.py ├── her.py ├── normalizer.py ├── replay_buffer.py ├── rollout.py └── util.py ├── logger.py ├── ppo1 ├── __init__.py ├── experiments │ └── train_cartpole.py ├── mlp_policy.py ├── pposgd_simple.py ├── run_atari.py ├── run_humanoid.py ├── run_mujoco.py └── run_robotics.py ├── ppo2 ├── __init__.py ├── ppo2.py ├── ppo2_2_sb_ppo_action_resolution.py ├── ppo2_3_sb_ppo_resolution_exploration_decay.py ├── run_atari.py └── run_mujoco.py ├── results_plotter.py └── trpo_mpi ├── __init__.py ├── run_atari.py ├── run_mujoco.py ├── trpo_mpi.py └── utils.py /.DS_Store: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/.DS_Store -------------------------------------------------------------------------------- /.gitignore: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/.gitignore -------------------------------------------------------------------------------- /1_sb_ppo_agent.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/1_sb_ppo_agent.py -------------------------------------------------------------------------------- /2_supermario_dqn.ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/2_supermario_dqn.ipynb -------------------------------------------------------------------------------- /4_pong_dqn (1).ipynb: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/4_pong_dqn (1).ipynb -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/README.md -------------------------------------------------------------------------------- /stable_baselines/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/__init__.py -------------------------------------------------------------------------------- /stable_baselines/a2c/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/a2c/__init__.py -------------------------------------------------------------------------------- /stable_baselines/a2c/a2c.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/a2c/a2c.py -------------------------------------------------------------------------------- /stable_baselines/a2c/run_atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/a2c/run_atari.py -------------------------------------------------------------------------------- /stable_baselines/a2c/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/a2c/utils.py -------------------------------------------------------------------------------- /stable_baselines/acer/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acer/__init__.py -------------------------------------------------------------------------------- /stable_baselines/acer/acer_simple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acer/acer_simple.py -------------------------------------------------------------------------------- /stable_baselines/acer/buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acer/buffer.py -------------------------------------------------------------------------------- /stable_baselines/acer/run_atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acer/run_atari.py -------------------------------------------------------------------------------- /stable_baselines/acktr/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/__init__.py -------------------------------------------------------------------------------- /stable_baselines/acktr/acktr_cont.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/acktr_cont.py -------------------------------------------------------------------------------- /stable_baselines/acktr/acktr_disc.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/acktr_disc.py -------------------------------------------------------------------------------- /stable_baselines/acktr/kfac.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/kfac.py -------------------------------------------------------------------------------- /stable_baselines/acktr/kfac_utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/kfac_utils.py -------------------------------------------------------------------------------- /stable_baselines/acktr/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/policies.py -------------------------------------------------------------------------------- /stable_baselines/acktr/run_atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/run_atari.py -------------------------------------------------------------------------------- /stable_baselines/acktr/run_mujoco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/run_mujoco.py -------------------------------------------------------------------------------- /stable_baselines/acktr/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/utils.py -------------------------------------------------------------------------------- /stable_baselines/acktr/value_functions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/acktr/value_functions.py -------------------------------------------------------------------------------- /stable_baselines/bench/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/bench/__init__.py -------------------------------------------------------------------------------- /stable_baselines/bench/benchmarks.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/bench/benchmarks.py -------------------------------------------------------------------------------- /stable_baselines/bench/monitor.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/bench/monitor.py -------------------------------------------------------------------------------- /stable_baselines/common/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/__init__.py -------------------------------------------------------------------------------- /stable_baselines/common/atari_wrappers.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/atari_wrappers.py -------------------------------------------------------------------------------- /stable_baselines/common/base_class.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/base_class.py -------------------------------------------------------------------------------- /stable_baselines/common/cg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/cg.py -------------------------------------------------------------------------------- /stable_baselines/common/cmd_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/cmd_util.py -------------------------------------------------------------------------------- /stable_baselines/common/console_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/console_util.py -------------------------------------------------------------------------------- /stable_baselines/common/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/dataset.py -------------------------------------------------------------------------------- /stable_baselines/common/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/distributions.py -------------------------------------------------------------------------------- /stable_baselines/common/filters.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/filters.py -------------------------------------------------------------------------------- /stable_baselines/common/identity_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/identity_env.py -------------------------------------------------------------------------------- /stable_baselines/common/input.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/input.py -------------------------------------------------------------------------------- /stable_baselines/common/math_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/math_util.py -------------------------------------------------------------------------------- /stable_baselines/common/misc_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/misc_util.py -------------------------------------------------------------------------------- /stable_baselines/common/mpi_adam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/mpi_adam.py -------------------------------------------------------------------------------- /stable_baselines/common/mpi_fork.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/mpi_fork.py -------------------------------------------------------------------------------- /stable_baselines/common/mpi_moments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/mpi_moments.py -------------------------------------------------------------------------------- /stable_baselines/common/mpi_running_mean_std.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/mpi_running_mean_std.py -------------------------------------------------------------------------------- /stable_baselines/common/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/policies.py -------------------------------------------------------------------------------- /stable_baselines/common/runners.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/runners.py -------------------------------------------------------------------------------- /stable_baselines/common/running_mean_std.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/running_mean_std.py -------------------------------------------------------------------------------- /stable_baselines/common/running_stat.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/running_stat.py -------------------------------------------------------------------------------- /stable_baselines/common/schedules.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/schedules.py -------------------------------------------------------------------------------- /stable_baselines/common/segment_tree.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/segment_tree.py -------------------------------------------------------------------------------- /stable_baselines/common/tf_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/tf_util.py -------------------------------------------------------------------------------- /stable_baselines/common/tile_images.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/tile_images.py -------------------------------------------------------------------------------- /stable_baselines/common/vec_env/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/vec_env/__init__.py -------------------------------------------------------------------------------- /stable_baselines/common/vec_env/base_vec_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/vec_env/base_vec_env.py -------------------------------------------------------------------------------- /stable_baselines/common/vec_env/dummy_vec_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/vec_env/dummy_vec_env.py -------------------------------------------------------------------------------- /stable_baselines/common/vec_env/subproc_vec_env.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/vec_env/subproc_vec_env.py -------------------------------------------------------------------------------- /stable_baselines/common/vec_env/vec_frame_stack.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/vec_env/vec_frame_stack.py -------------------------------------------------------------------------------- /stable_baselines/common/vec_env/vec_normalize.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/common/vec_env/vec_normalize.py -------------------------------------------------------------------------------- /stable_baselines/ddpg/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ddpg/__init__.py -------------------------------------------------------------------------------- /stable_baselines/ddpg/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ddpg/ddpg.py -------------------------------------------------------------------------------- /stable_baselines/ddpg/main.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ddpg/main.py -------------------------------------------------------------------------------- /stable_baselines/ddpg/memory.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ddpg/memory.py -------------------------------------------------------------------------------- /stable_baselines/ddpg/noise.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ddpg/noise.py -------------------------------------------------------------------------------- /stable_baselines/ddpg/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ddpg/policies.py -------------------------------------------------------------------------------- /stable_baselines/deepq/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/__init__.py -------------------------------------------------------------------------------- /stable_baselines/deepq/build_graph.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/build_graph.py -------------------------------------------------------------------------------- /stable_baselines/deepq/dqn.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/dqn.py -------------------------------------------------------------------------------- /stable_baselines/deepq/dqn_10_sb_dqn_supermari_decay_resolution_exploration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/dqn_10_sb_dqn_supermari_decay_resolution_exploration.py -------------------------------------------------------------------------------- /stable_baselines/deepq/dqn_12_sb_dqn_supermari_decay_resolution_exploration_step_10.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/dqn_12_sb_dqn_supermari_decay_resolution_exploration_step_10.py -------------------------------------------------------------------------------- /stable_baselines/deepq/dqn_13_sb_dqn_supermari_decay_resolution_exploration_step_20_exploration_term_5000.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/dqn_13_sb_dqn_supermari_decay_resolution_exploration_step_20_exploration_term_5000.py -------------------------------------------------------------------------------- /stable_baselines/deepq/dqn_14_resoultion_network.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/dqn_14_resoultion_network.py -------------------------------------------------------------------------------- /stable_baselines/deepq/dqn_9_sb_dqn_supermari_resolution_exploration.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/dqn_9_sb_dqn_supermari_resolution_exploration.py -------------------------------------------------------------------------------- /stable_baselines/deepq/experiments/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /stable_baselines/deepq/experiments/custom_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/experiments/custom_cartpole.py -------------------------------------------------------------------------------- /stable_baselines/deepq/experiments/enjoy_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/experiments/enjoy_cartpole.py -------------------------------------------------------------------------------- /stable_baselines/deepq/experiments/enjoy_mountaincar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/experiments/enjoy_mountaincar.py -------------------------------------------------------------------------------- /stable_baselines/deepq/experiments/enjoy_pong.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/experiments/enjoy_pong.py -------------------------------------------------------------------------------- /stable_baselines/deepq/experiments/run_atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/experiments/run_atari.py -------------------------------------------------------------------------------- /stable_baselines/deepq/experiments/train_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/experiments/train_cartpole.py -------------------------------------------------------------------------------- /stable_baselines/deepq/experiments/train_mountaincar.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/experiments/train_mountaincar.py -------------------------------------------------------------------------------- /stable_baselines/deepq/policies.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/policies.py -------------------------------------------------------------------------------- /stable_baselines/deepq/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/replay_buffer.py -------------------------------------------------------------------------------- /stable_baselines/deepq/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/deepq/utils.py -------------------------------------------------------------------------------- /stable_baselines/gail/__init__.py: -------------------------------------------------------------------------------- 1 | from stable_baselines.gail.model import GAIL 2 | -------------------------------------------------------------------------------- /stable_baselines/gail/adversary.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/adversary.py -------------------------------------------------------------------------------- /stable_baselines/gail/behavior_clone.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/behavior_clone.py -------------------------------------------------------------------------------- /stable_baselines/gail/dataset/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /stable_baselines/gail/dataset/mujocodset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/dataset/mujocodset.py -------------------------------------------------------------------------------- /stable_baselines/gail/gail_eval.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/gail_eval.py -------------------------------------------------------------------------------- /stable_baselines/gail/mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/mlp_policy.py -------------------------------------------------------------------------------- /stable_baselines/gail/model.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/model.py -------------------------------------------------------------------------------- /stable_baselines/gail/result/HalfCheetah-normalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/HalfCheetah-normalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/HalfCheetah-normalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/HalfCheetah-normalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/HalfCheetah-unnormalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/HalfCheetah-unnormalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/HalfCheetah-unnormalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/HalfCheetah-unnormalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Hopper-normalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Hopper-normalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Hopper-normalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Hopper-normalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Hopper-unnormalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Hopper-unnormalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Hopper-unnormalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Hopper-unnormalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Humanoid-normalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Humanoid-normalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Humanoid-normalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Humanoid-normalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Humanoid-unnormalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Humanoid-unnormalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Humanoid-unnormalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Humanoid-unnormalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/HumanoidStandup-normalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/HumanoidStandup-normalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/HumanoidStandup-normalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/HumanoidStandup-normalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/HumanoidStandup-unnormalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/HumanoidStandup-unnormalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/HumanoidStandup-unnormalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/HumanoidStandup-unnormalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Walker2d-normalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Walker2d-normalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Walker2d-normalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Walker2d-normalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Walker2d-unnormalized-deterministic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Walker2d-unnormalized-deterministic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/Walker2d-unnormalized-stochastic-scores.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/Walker2d-unnormalized-stochastic-scores.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/gail-result.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/gail-result.md -------------------------------------------------------------------------------- /stable_baselines/gail/result/halfcheetah-training.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/halfcheetah-training.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/hopper-training.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/hopper-training.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/humanoid-training.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/humanoid-training.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/humanoidstandup-training.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/humanoidstandup-training.png -------------------------------------------------------------------------------- /stable_baselines/gail/result/walker2d-training.png: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/result/walker2d-training.png -------------------------------------------------------------------------------- /stable_baselines/gail/run_mujoco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/run_mujoco.py -------------------------------------------------------------------------------- /stable_baselines/gail/statistics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/gail/statistics.py -------------------------------------------------------------------------------- /stable_baselines/her/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/__init__.py -------------------------------------------------------------------------------- /stable_baselines/her/actor_critic.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/actor_critic.py -------------------------------------------------------------------------------- /stable_baselines/her/ddpg.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/ddpg.py -------------------------------------------------------------------------------- /stable_baselines/her/experiment/__init__.py: -------------------------------------------------------------------------------- 1 | -------------------------------------------------------------------------------- /stable_baselines/her/experiment/config.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/experiment/config.py -------------------------------------------------------------------------------- /stable_baselines/her/experiment/play.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/experiment/play.py -------------------------------------------------------------------------------- /stable_baselines/her/experiment/plot.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/experiment/plot.py -------------------------------------------------------------------------------- /stable_baselines/her/experiment/train.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/experiment/train.py -------------------------------------------------------------------------------- /stable_baselines/her/her.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/her.py -------------------------------------------------------------------------------- /stable_baselines/her/normalizer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/normalizer.py -------------------------------------------------------------------------------- /stable_baselines/her/replay_buffer.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/replay_buffer.py -------------------------------------------------------------------------------- /stable_baselines/her/rollout.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/rollout.py -------------------------------------------------------------------------------- /stable_baselines/her/util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/her/util.py -------------------------------------------------------------------------------- /stable_baselines/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/logger.py -------------------------------------------------------------------------------- /stable_baselines/ppo1/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo1/__init__.py -------------------------------------------------------------------------------- /stable_baselines/ppo1/experiments/train_cartpole.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo1/experiments/train_cartpole.py -------------------------------------------------------------------------------- /stable_baselines/ppo1/mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo1/mlp_policy.py -------------------------------------------------------------------------------- /stable_baselines/ppo1/pposgd_simple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo1/pposgd_simple.py -------------------------------------------------------------------------------- /stable_baselines/ppo1/run_atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo1/run_atari.py -------------------------------------------------------------------------------- /stable_baselines/ppo1/run_humanoid.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo1/run_humanoid.py -------------------------------------------------------------------------------- /stable_baselines/ppo1/run_mujoco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo1/run_mujoco.py -------------------------------------------------------------------------------- /stable_baselines/ppo1/run_robotics.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo1/run_robotics.py -------------------------------------------------------------------------------- /stable_baselines/ppo2/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo2/__init__.py -------------------------------------------------------------------------------- /stable_baselines/ppo2/ppo2.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo2/ppo2.py -------------------------------------------------------------------------------- /stable_baselines/ppo2/ppo2_2_sb_ppo_action_resolution.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo2/ppo2_2_sb_ppo_action_resolution.py -------------------------------------------------------------------------------- /stable_baselines/ppo2/ppo2_3_sb_ppo_resolution_exploration_decay.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo2/ppo2_3_sb_ppo_resolution_exploration_decay.py -------------------------------------------------------------------------------- /stable_baselines/ppo2/run_atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo2/run_atari.py -------------------------------------------------------------------------------- /stable_baselines/ppo2/run_mujoco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/ppo2/run_mujoco.py -------------------------------------------------------------------------------- /stable_baselines/results_plotter.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/results_plotter.py -------------------------------------------------------------------------------- /stable_baselines/trpo_mpi/__init__.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/trpo_mpi/__init__.py -------------------------------------------------------------------------------- /stable_baselines/trpo_mpi/run_atari.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/trpo_mpi/run_atari.py -------------------------------------------------------------------------------- /stable_baselines/trpo_mpi/run_mujoco.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/trpo_mpi/run_mujoco.py -------------------------------------------------------------------------------- /stable_baselines/trpo_mpi/trpo_mpi.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/trpo_mpi/trpo_mpi.py -------------------------------------------------------------------------------- /stable_baselines/trpo_mpi/utils.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wonseokjung/ai_supermario/HEAD/stable_baselines/trpo_mpi/utils.py --------------------------------------------------------------------------------