Super-Mario-Bros-RL
This project explores deep reinforcement learning, hybrid actor-critic approach with A3C/PPO combined with curiosity for playing Super Mario Bros
파일 탐색기
최종 버전 다운로드 (.zip)- __init__.py
- atari_wrapper.py
- mario_actions.py
- __init__.py
- actor_critic.py
- icm.py
- __init__.py
- sharedadam.py
- mario_a3c_params.pkl
- mario_a3c_params_curiosity.pkl
- mario_curves.csv
- train_reward_0.csv
- train_reward_1.csv
- train_reward_10.csv
- train_reward_11.csv
- train_reward_12.csv
- train_reward_13.csv
- train_reward_14.csv
- train_reward_15.csv
- train_reward_16.csv
- train_reward_17.csv
- train_reward_18.csv
- train_reward_19.csv
- train_reward_2.csv
- train_reward_20.csv
- train_reward_21.csv
- train_reward_22.csv
- train_reward_3.csv
- train_reward_4.csv
- train_reward_5.csv
- train_reward_6.csv
- train_reward_7.csv
- train_reward_8.csv
- train_reward_9.csv
- mario_a3c_params.pkl
- mario_a3c_params_curiosity.pkl
- mario_curves.csv
- train_reward_0.csv
- train_reward_1.csv
- train_reward_10.csv
- train_reward_11.csv
- train_reward_12.csv
- train_reward_13.csv
- train_reward_14.csv
- train_reward_15.csv
- train_reward_16.csv
- train_reward_17.csv
- train_reward_18.csv
- train_reward_19.csv
- train_reward_2.csv
- train_reward_20.csv
- train_reward_21.csv
- train_reward_22.csv
- train_reward_3.csv
- train_reward_4.csv
- train_reward_5.csv
- train_reward_6.csv
- train_reward_7.csv
- train_reward_8.csv
- train_reward_9.csv
- mario_a3c_params.pkl
- mario_curves.csv
- train_reward_0.csv
- train_reward_1.csv
- train_reward_10.csv
- train_reward_11.csv
- train_reward_12.csv
- train_reward_13.csv
- train_reward_14.csv
- train_reward_15.csv
- train_reward_16.csv
- train_reward_17.csv
- train_reward_18.csv
- train_reward_19.csv
- train_reward_2.csv
- train_reward_20.csv
- train_reward_21.csv
- train_reward_22.csv
- train_reward_3.csv
- train_reward_4.csv
- train_reward_5.csv
- train_reward_6.csv
- train_reward_7.csv
- train_reward_8.csv
- train_reward_9.csv
- mario_a3c_params.pkl
- mario_curves.csv
- train_reward_0.csv
- train_reward_1.csv
- train_reward_10.csv
- train_reward_11.csv
- train_reward_12.csv
- train_reward_13.csv
- train_reward_14.csv
- train_reward_15.csv
- train_reward_16.csv
- train_reward_17.csv
- train_reward_18.csv
- train_reward_19.csv
- train_reward_2.csv
- train_reward_20.csv
- train_reward_21.csv
- train_reward_22.csv
- train_reward_3.csv
- train_reward_4.csv
- train_reward_5.csv
- train_reward_6.csv
- train_reward_7.csv
- train_reward_8.csv
- train_reward_9.csv
- __init__.py
- train.py
- train_curiosity.py
- __init__.py
- __init__.py
- font_color.py
- first_test.mp4
- mario.gif
- openaigym.episode_batch.1.8944.stats.json
- openaigym.manifest.1.8944.manifest.json
- openaigym.video.1.8944.video000000.meta.json
- openaigym.video.1.8944.video000000.mp4
- dense_ppo_plot.png
- DQN.ipynb
- README.md
- record.ipynb
- train-mario-curiosity.py
- train-mario.py
- dense_plot.png
- dense_ppo_plot.png
- sparse_plot.png
- sparse_ppo_plot.png
- __init__.py
- a2c_acktr.py
- kfac.py
- ppo.py
- __init__.py
- actor_critic.py
- arguments.py
- distributions.py
- envs.py
- icm.py
- model.py
- storage.py
- utils.py
- visualize.py
- __init__.py
- atari_wrapper.py
- mario_actions.py
- eval_reward.csv
- train_reward0.csv
- train_reward1.csv
- train_reward10.csv
- train_reward11.csv
- train_reward2.csv
- train_reward3.csv
- train_reward4.csv
- train_reward5.csv
- train_reward6.csv
- train_reward7.csv
- train_reward8.csv
- train_reward9.csv
- eval_reward.csv
- train_reward0.csv
- train_reward1.csv
- train_reward10.csv
- train_reward11.csv
- train_reward2.csv
- train_reward3.csv
- train_reward4.csv
- train_reward5.csv
- train_reward6.csv
- train_reward7.csv
- train_reward8.csv
- train_reward9.csv
- eval.ipynb
- main.py
- README.md
- requirements.txt
- setup.py
- Exploring Deep Reinforcement Learning with Super Mario Bros.pdf
- LICENSE
- README.md
// repository documentation
Was this content helpful?
(0 ratings)