论文Reinforcement Learning with Deep Energy-Based Policies 在策略中引入熵，定义了softQ、softV， 给出了soft Bellman Equation、策略提升定理，证明了soft Q可以通过soft Bellman Equation迭代收敛。
proof.pdf 对以上内容进行推导。
-
Notifications
You must be signed in to change notification settings - Fork 0
Git-123-Hub/soft-Q-learning-proof
About
对soft Q-learning论文中的公式进行证明
Resources
Stars
Watchers
Forks
Releases
No releases published
Packages 0
No packages published