Skip to content
conftrace_
2025 ICML ICML 2025

Penalizing Infeasible Actions and Reward Scaling in Reinforcement Learning with Offline Data

Abstract

No abstract available. No abstract was captured for this paper when its proceedings were scraped - most often an older edition published without one online. How the corpus is built.

Authors

Jeonghye Kim, Yongjae Shin, Whiyoung Jung, Sunghoon Hong, Deunsol Yoon, Youngchul Sung, Kanghoon Lee, Woohyung Lim

Topics

Reinforcement Learning > Methods > Offline RL

Keywords

layer normalization d4rl benchmark offline data reward scaling penalization mechanism q-value extrapolation errors
Download PDF