This is a heavily interactive web application, and JavaScript is required. Simple HTML interfaces are possible, but that is not what this is.
Post
TMLR Published Papers
tmlr-pub.bsky.social
did:plc:vvhlcsj2kue7tnl3jxfxsdxs
MoMA: Model-based Mirror Ascent for Offline Reinforcement Learning
Mao Hong, Zhiyue Zhang, Yue Wu, Yanxun Xu
Action editor: Shixiang Gu
https://openreview.net/forum?id=RHUKg8n9tw
#offline #reinforcement #policy
2024-12-13T13:06:54.556Z