Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning

ArXi:2606.00780v1 Announce Type: cross Offline meta-reinforcement learning leverages static datasets to enable agents to generalize to unseen environments by combining offline efficiency with meta-learning adaptability, yet it faces key challenges from context and policy distribution shifts. These issues hinder agents from adapting to online environments, and are further exacerbated under sparse-reward settings. As a result, agents often become trapped in an inherent pattern dilemma, failing to achieve robust generalization.