OER: Offline Experience Replay for Continual Offline Reinforcement Learning

arXiv:2305.13804v2 Announce Type: replace
Abstract: The capability of continuously learning new skills via a sequence of pre-collected offline datasets is desired for an agent. However, consecutively learning a sequence of offline tasks likely leads to the catastrophic forgetting issue under resource-limited scenarios. In this paper, we formulate a new setting, continual offline reinforcement learning (CORL), where an agent learns a sequence of offline reinforcement learning tasks and pursues good performance on all learned tasks with a small replay buffer without …

abstract agent arxiv capability catastrophic forgetting continual cs.lg datasets experience however issue leads offline paper reinforcement reinforcement learning skills tasks type via