csuhyd / curlingrobot

Curling Robot @ TongYe

CurlingRobot

Curling Robot @ TongYe

Choose RL Methods：

Continuous Action Space :

• Policy gradient
• DDPG
• A3C
• PPO

Discrete Action Space:

• Q-learning
• DQN
• A3C
• PPO

reference

[1] https://blog.csdn.net/kenneth_yu/article/details/78478356 DDPG

[2] https://www.ibm.com/developerworks/cn/analytics/library/ba-lo-deep-introduce-policy-gradient/index.html Policy Gradient (PG)

[6] https://medium.com/@jonathan_hui/rl-policy-gradients-explained-9b13b688b146 Jonathan Hui, Medium Blog 最好的blog

[4] https://morvanzhou.github.io/tutorials/machine-learning/reinforcement-learning/5-1-policy-gradient-softmax1/ 莫烦

[5] https://www.bilibili.com/video/av35757082/?p=28 李宏毅深度学习视频

[6] https://blog.csdn.net/LagrangeSK/article/details/81010195 强化学习教程Blog，讲的很详细，结合大神的PPTT

ps：李宏毅牛逼，需要过一遍讲义