强化学习RL 05: Alpha Go、Alpha Zero

目录

1. Alpha Go

1.1 Behavior Cloning

1.2 reinforcement learning of policy network

1.3 Alpha Zero

1.4 Monte-Carlo Tree Search

参考

1. Alpha Go

• alphaGo actually uses a 19*19*48 tensor to store other information.
• number of possible sequence of actions is 
• training in 3 steps:
  • initialize policy network using behavior cloning.
  • train the policy network using policy gradient.
  • after training the policy network, use it to train a value network.
• Execution (actually play Go games)
  • Do Monte Carlo Tree Search (MCTS) using the policy and value networks.

1.1 Behavior Cloning

Behavior cloning is imitation learning rather than reinforcement learning.

problem：会对未见过的操作懵逼，然后break down。

1.2 reinforcement learning of policy network

1.3 Alpha Zero

• AlphaGo Zero does not use human experience. (no behavior cloning)

1.4 Monte-Carlo Tree Search

• step 1: Selection
• step 2: Expansion
• step 3: Evaluation
• step 4: Backup

参考

1. 王树森~强化学习 Reinforcement Learning

2.  https://www.cnblogs.com/pinard/category/1254674.html

本文来自互联网用户投稿，文章观点仅代表作者本人，不代表本站立场，不承担相关法律责任。如若转载，请注明出处。 如若内容造成侵权/违法违规/事实不符，请点击【内容举报】进行投诉反馈！