使用Gym庫+keras實現強化學習算法

【時間】2019.12.11

【題目】使用Gym庫+keras實現強化學習算法

一、Gym庫介紹與使用

gym 介紹

二、例子

Keras深度強化學習-- Policy Network與DQN實現

相關資源：

Paper：
Policy Gradient:Policy gradient methods for reinforcement learning with function approximation
DQN: Playing Atari with Deep Reinforcement Learning
NatureDQN:Human-level control through deep reinforcement learning

 

Github：https://github.com/xiaochus/Deep-Reinforcement-Learning-Practice

這是一個用keras實現的深度強化學習相關算法的資源code

Algorithm

#	Name	Paper
1	DQN	Playing Atari with Deep Reinforcement Learning
2	Nature DQN	Human-level control through deep reinforcement learning
3	Double DQN	Deep Reinforcement Learning with Double Q-learning
4	Dueling DQN	Dueling Network Architectures for Deep Reinforcement Learning
5	Actor-Critic	Actor-Critic Algorithms
6	Policy Network	Policy gradient methods for reinforcement learning with function approximation
7	DDPG	Continuous Control with Deep Reinforcement Learning
8	PPO_TF	Proximal Policy Optimization Algorithms
9	A3C	Asynchronous Methods for Deep Reinforcement Learning