# Reinforcement_Learning

**Repository Path**: yangwulve/Reinforcement_Learning

## Basic Information

- **Project Name**: Reinforcement_Learning
- **Description**: ProjectTwo_RL
- **Primary Language**: Unknown
- **License**: Not specified
- **Default Branch**: master
- **Homepage**: None
- **GVP Project**: No

## Statistics

- **Stars**: 0
- **Forks**: 0
- **Created**: 2020-05-23
- **Last Updated**: 2020-12-19

## Categories & Tags

**Categories**: Uncategorized

**Tags**: None

## README

#RLAI书籍阅读计划:
```
./book  目录下
``` 
08_20  QL算法+RLAI chapter2  
08_21  RLAI chapter2   
.   
.   
.   
09_03 完成RLAI前十三章的阅读   


**Deep Reinforcement Learning Algorithm**    
代码: 
```
./Pytorch_basic  目录下
```
*一.deepmind DQN*
测试环境:gym cartpole-v0  实现了以下几种DQN变型     
1.DQN     
2.DoubleCQN  
3.PriorityMemoryDQN  
4.DuelingDQN  
5.DeepRecurrentQN  
6...... e.g. AverageDQN  NoisyDQN RainBow等等尚未实现  

*二.openai policyGradient*   
若干变型  尚未实现  



**区别理解**   
1.on-policy off-policy actor-critic区别？  
2.value-based policy-based区别？ 

*