Task-Aware Exploration via a Predictive Bisimulation Metric
arXiv:2602.18724v1 Announce Type: new Abstract: Accelerating exploration in visual reinforcement learning under sparse rewards remains challenging due to the substantial task-irrelevant variations. Despite advances in …
Dayang Liang, Ruihan Liu, Lipeng Wan, Yunlong Liu, Bo An
조회수 23회