bellman-residual

标签

Cards List
#bellman-residual

CODS: Iterative Bellman-Residual Data Selection for Reusable Offline Reinforcement Learning

arXiv cs.LG · 昨天 缓存

Introduces CODS, an iterative critic-guided data selection method for offline reinforcement learning that retains task performance at low data budgets by selecting high-residual transitions over multiple rounds.

0 人收藏 0 人点赞
← 返回首页

提交意见反馈