bacow/easy-rl
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Update Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.md

Browse Source
This commit is contained in:
Yiyuan Yang
2022-11-20 23:36:41 +08:00
committed by GitHub
parent cfd43ea78d
commit e7b7972acf
1 changed files with 5 additions and 1 deletions
Download Patch File Download Diff File Expand all files Collapse all files

6
papers/Policy_gradient/Soft Actor-Critic_Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor.md
View File

@@ -157,7 +157,11 @@ soft actor-critic算法用伪代码可表示为：
虽然SAC算法采用了energy-based模型，但是实际上策略分布仍为高斯分布，存在一定的局限性。 虽然SAC算法采用了energy-based模型，但是实际上策略分布仍为高斯分布，存在一定的局限性。
====================================
作者：杨骏铭
研究单位：南京邮电大学
研究方向：强化学习、对抗学习
联系邮箱：jmingyang@outlook.com