Solving Continual Offline Reinforcement Learning with Decision Transformer

arXiv:2401.08478v2 Announce Type: replace
Abstract: Continuous offline reinforcement learning (CORL) combines continuous and offline reinforcement learning, enabling agents to learn multiple tasks from static datasets without forgetting prior tasks. However, CORL faces challenges in balancing stability and plasticity. Existing methods, employing Actor-Critic structures and experience replay (ER), suffer from distribution shifts, low efficiency, and weak knowledge-sharing. We aim to investigate whether Decision Transformer (DT), another offline RL paradigm, can serve as a more suitable offline continuous learner to address these …

abstract actor actor-critic agents arxiv challenges continual continuous corl cs.ai cs.lg datasets decision distribution enabling experience however learn low multiple offline prior reinforcement reinforcement learning stability tasks transformer type