Sergey Levine· svlevine·· 2 小时前AI 评分46
优势条件监督提取策略实现RL最优
Turns out that simply extracting policies with supervised learning conditioned on the advantage can get state of the art results in RL, a...
AI 导读
事实证明，只要把几个重要细节做对，仅用基于优势（advantage）的监督学习来提取策略，就能在强化学习（RL）中取得最先进（state of the art）的结果！
来源：Sergey Levine · x.com