├── Doing_RL_with_PPO.pdf ├── README.md ├── openai_baselines_ppo ├── console_util.py ├── dataset.py ├── distributions.py ├── logger.py ├── math_util.py ├── misc_util.py ├── mlp_policy.py ├── mpi_adam.py ├── mpi_moments.py ├── mpi_running_mean_std.py ├── pposgd_simple.py ├── run_roboschool.py ├── save │ ├── Humanoid-v1.data-00000-of-00001 │ ├── Humanoid-v1.index │ └── Humanoid-v1.meta ├── test_roboschool.py └── tf_util.py └── ppo.py /Doing_RL_with_PPO.pdf: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/Doing_RL_with_PPO.pdf -------------------------------------------------------------------------------- /README.md: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/README.md -------------------------------------------------------------------------------- /openai_baselines_ppo/console_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/console_util.py -------------------------------------------------------------------------------- /openai_baselines_ppo/dataset.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/dataset.py -------------------------------------------------------------------------------- /openai_baselines_ppo/distributions.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/distributions.py -------------------------------------------------------------------------------- /openai_baselines_ppo/logger.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/logger.py -------------------------------------------------------------------------------- /openai_baselines_ppo/math_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/math_util.py -------------------------------------------------------------------------------- /openai_baselines_ppo/misc_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/misc_util.py -------------------------------------------------------------------------------- /openai_baselines_ppo/mlp_policy.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/mlp_policy.py -------------------------------------------------------------------------------- /openai_baselines_ppo/mpi_adam.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/mpi_adam.py -------------------------------------------------------------------------------- /openai_baselines_ppo/mpi_moments.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/mpi_moments.py -------------------------------------------------------------------------------- /openai_baselines_ppo/mpi_running_mean_std.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/mpi_running_mean_std.py -------------------------------------------------------------------------------- /openai_baselines_ppo/pposgd_simple.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/pposgd_simple.py -------------------------------------------------------------------------------- /openai_baselines_ppo/run_roboschool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/run_roboschool.py -------------------------------------------------------------------------------- /openai_baselines_ppo/save/Humanoid-v1.data-00000-of-00001: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/save/Humanoid-v1.data-00000-of-00001 -------------------------------------------------------------------------------- /openai_baselines_ppo/save/Humanoid-v1.index: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/save/Humanoid-v1.index -------------------------------------------------------------------------------- /openai_baselines_ppo/save/Humanoid-v1.meta: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/save/Humanoid-v1.meta -------------------------------------------------------------------------------- /openai_baselines_ppo/test_roboschool.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/test_roboschool.py -------------------------------------------------------------------------------- /openai_baselines_ppo/tf_util.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/openai_baselines_ppo/tf_util.py -------------------------------------------------------------------------------- /ppo.py: -------------------------------------------------------------------------------- https://raw.githubusercontent.com/wooridle/DeepRL-PPO-tutorial/HEAD/ppo.py --------------------------------------------------------------------------------