fennuDetudou / RL_fundation Public

Notifications You must be signed in to change notification settings
Fork 1
Star 0

强化学习基础算法的TensorFlow实现，包括SARSA,Q-LEARNING,PG,DQN,AC算法

0 stars 1 fork Branches Tags Activity

Notifications

Name		Name	Last commit message	Last commit date
Latest commit History 3 Commits
AC		AC
DQN		DQN
Policy Gradiant		Policy Gradiant
Q-learning		Q-learning
SARSA		SARSA
README.md		README.md

Repository files navigation

RL_fundation

强化学习基础算法的TensorFlow实现，包括SARSA,Q-LEARNING,PG,DQN,AC算法

深度强化学习部分算法主要参考了莫凡老师的算法部分，做了小部分更改以及更为详尽的注释

DQN

算法包括以下三个实现，DDQN，DQN,duelingDQN,以脚本的形式运行，参数为 parser.add_argument('--model',default='dqn',help='input the method')

About

强化学习基础算法的TensorFlow实现，包括SARSA,Q-LEARNING,PG,DQN,AC算法

Report repository

Releases

No releases published

Packages

No packages published

Languages

Python 100.0%