---
title: "RL"
date: 2018-12-29
lastmod: 2020-01-05
weight: 5
type: 
icon: #
description: "人工智能中阶路线图,RL"
# search related keywords
---


- 基本RL训练方法
- Q-learning和Policy Gradient的提升
- Exploration问题
- Immitation Learning


## 相关学习资源

### 基本RL训练方法

见<https://youtu.be/8EcdaCk9KaQ>


### Q-learning和Policy Gradient的提升

这方面paper比较多，见<https://arxiv.org/abs/1710.02298>、<https://arxiv.org/abs/1707.06347>、<https://arxiv.org/abs/1801.01290>等


### Exploration问题

见<https://www.researchgate.net/profile/Mohamed_Mourad_Lafifi/post/Considering_robotic_exploration_in_unknown_environment_is_there_any_parameters_that_could_bias_exploration_decision/attachment/5c89eb67cfe4a72994957bce/AS%3A736230840995840%401552542519031/download/A+Survey+of+Exploration+Strategies+in+Reinforcement+Learning++Roger+McFarlane.pdf>及后续研究


### Immitation Learning

见<http://www.open-access.bcu.ac.uk/5045/1/Imitation%20Learning%20A%20Survey%20of%20Learning%20Methods.pdf>及后续研究