Offline Trajectory Generalization for Offline Reinforcement Learning

arXiv:2404.10393v1 Announce Type: new
Abstract: Offline reinforcement learning (RL) aims to learn policies from static datasets of previously collected trajectories. Existing methods for offline RL either constrain the learned policy to the support of offline data or utilize model-based virtual environments to generate simulated rollouts. However, these methods suffer from (i) poor generalization to unseen states; and (ii) trivial improvement from low-qualified rollout simulation. In this paper, we propose offline trajectory generalization through world transformers for offline reinforcement learning (OTTO). …

abstract arxiv cs.ai cs.lg data datasets environments generate however learn offline policies policy reinforcement reinforcement learning support trajectory type virtual virtual environments