Reinforcement-learning-with-tensorflow-master
所属分类:人工智能/神经网络/深度学习
开发工具:Python
文件大小:186KB
下载次数:28
上传日期:2018-02-09 16:59:13
上 传 者:
Mr.Ho
说明: 各种强化学习代码,强化学习(reinforcement learning),又称再励学习、评价学习,是一种重要的机器学习方法,在智能控制机器人及分析预测等领域有许多应用。
(Reinforcement learning (reinforcement learning), also known as reinforcement learning and evaluation learning, is an important machine learning method. It has many applications in intelligent control robots, analysis and prediction.)
文件列表:
contents\10_A3C\A3C_continuous_action.py (8150, 2017-09-13)
contents\10_A3C\A3C_discrete_action.py (7897, 2017-09-13)
contents\10_A3C\A3C_RNN.py (9425, 2017-09-13)
contents\11_Dyna_Q\maze_env.py (3898, 2017-09-13)
contents\11_Dyna_Q\RL_brain.py (2915, 2017-09-13)
contents\11_Dyna_Q\run_this.py (1500, 2017-09-13)
contents\12_Proximal_Policy_Optimization\DPPO.py (8263, 2017-09-13)
contents\12_Proximal_Policy_Optimization\simply_PPO.py (6465, 2017-09-13)
contents\1_command_line_reinforcement_learning\treasure_on_right.py (3346, 2017-09-13)
contents\2_Q_Learning_maze\maze_env.py (4251, 2017-09-13)
contents\2_Q_Learning_maze\RL_brain.py (1814, 2017-09-13)
contents\2_Q_Learning_maze\run_this.py (1388, 2017-09-13)
contents\3_Sarsa_maze\maze_env.py (3956, 2017-09-13)
contents\3_Sarsa_maze\RL_brain.py (2671, 2017-09-13)
contents\3_Sarsa_maze\run_this.py (1510, 2017-09-13)
contents\4_Sarsa_lambda_maze\maze_env.py (3957, 2017-09-13)
contents\4_Sarsa_lambda_maze\RL_brain.py (3138, 2017-09-13)
contents\4_Sarsa_lambda_maze\run_this.py (1602, 2017-09-13)
contents\5.1_Double_DQN\RL_brain.py (6678, 2017-09-13)
contents\5.1_Double_DQN\run_Pendulum.py (2133, 2017-09-13)
contents\5.2_Prioritized_Replay_DQN\RL_brain.py (11847, 2017-09-13)
contents\5.2_Prioritized_Replay_DQN\run_MountainCar.py (2113, 2017-09-13)
contents\5.3_Dueling_DQN\RL_brain.py (6714, 2017-09-13)
contents\5.3_Dueling_DQN\run_Pendulum.py (2159, 2017-09-13)
contents\5_Deep_Q_Network\DQN_modified.py (6537, 2017-09-13)
contents\5_Deep_Q_Network\maze_env.py (4165, 2017-09-13)
contents\5_Deep_Q_Network\RL_brain.py (8416, 2017-09-13)
contents\5_Deep_Q_Network\run_this.py (1342, 2017-09-13)
contents\6_OpenAI_gym\RL_brain.py (8416, 2017-09-13)
contents\6_OpenAI_gym\run_CartPole.py (1475, 2017-09-13)
contents\6_OpenAI_gym\run_MountainCar.py (1355, 2017-09-13)
contents\7_Policy_gradient_softmax\RL_brain.py (4346, 2017-09-13)
contents\7_Policy_gradient_softmax\run_CartPole.py (1815, 2017-09-13)
contents\7_Policy_gradient_softmax\run_MountainCar.py (2025, 2017-09-13)
contents\8_Actor_Critic_Advantage\AC_CartPole.py (5860, 2017-09-13)
contents\8_Actor_Critic_Advantage\AC_continue_Pendulum.py (6405, 2017-09-13)
contents\9_Deep_Deterministic_Policy_Gradient_DDPG\DDPG.py (9931, 2017-09-13)
contents\9_Deep_Deterministic_Policy_Gradient_DDPG\DDPG_update.py (5755, 2017-09-13)
experiments\2D_car\car_env.py (7953, 2017-09-13)
experiments\2D_car\collision.py (2072, 2017-09-13)
... ...
# Reinforcement Learning Methods and Tutorials
In these tutorials for reinforcement learning, it covers from the basic RL algorithms to advanced algorithms developed recent years.
**If you speak Chinese, visit [莫烦 Python](https://morvanzhou.github.io/tutorials/) or my [Youtube channel](https://www.youtube.com/channel/UCdyjiB5H8Pu7aDTNVXTTpcg) for more.**
**As many requests about making these tutorials available in English, please find them in this playlist:** ([https://www.youtube.com/playlist?list=PLXO45tsB95cIplu-fLMpUEEZTwrDNh6Ba](https://www.youtube.com/playlist?list=PLXO45tsB95cIplu-fLMpUEEZTwrDNh6Ba))
# Table of Contents
* Tutorials
* [Simple entry example](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/1_command_line_reinforcement_learning)
* [Q-learning](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/2_Q_Learning_maze)
* [Sarsa](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/3_Sarsa_maze)
* [Sarsa(lambda)](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/4_Sarsa_lambda_maze)
* [Deep Q Network](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/5_Deep_Q_Network)
* [Using OpenAI Gym](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/6_OpenAI_gym)
* [Double DQN](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/5.1_Double_DQN)
* [DQN with Prioitized Experience Replay](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/5.2_Prioritized_Replay_DQN)
* [Dueling DQN](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/5.3_Dueling_DQN)
* [Policy Gradients](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/7_Policy_gradient_softmax)
* [Actor Critic](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/8_Actor_Critic_Advantage)
* [Deep Deterministic Policy Gradient](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/9_Deep_Deterministic_Policy_Gradient_DDPG)
* [A3C](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/10_A3C)
* [Dyna-Q](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/11_Dyna_Q)
* [Proximal Policy Optimization (PPO)](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/contents/12_Proximal_Policy_Optimization)
* [Some of my experients](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/experiments)
* [2D Car](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/experiments/2D_car)
* [Robot arm](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/experiments/Robot_arm)
* [BipedalWalker](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/experiments/Solve_BipedalWalker)
* [LunarLander](https://github.com/MorvanZhou/Reinforcement-learning-with-tensorflow/tree/master/experiments/Solve_LunarLander)
# Donation
*If this does help you, please consider donating to support me for better tutorials. Any contribution is greatly appreciated!*
近期下载者:
相关文件:
收藏者: