{"ID":2922128,"CreatedAt":"2026-06-02T02:42:49.606572591Z","UpdatedAt":"2026-06-02T15:47:14.09534485Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2606.00780","arxiv_id":"2606.00780","title":"Behavior-Invariant Task Representation Learning with Transformer-based World Models for Offline Meta-Reinforcement Learning","abstract":"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. In this work, we propose a novel framework that integrates information-theoretic task representation learning with a Transformer-based stochastic world model. Our approach extracts task-defining latent variables that are invariant to behavior policy, thereby effectively mitigating the context distribution shift. To further handle policy shift and model exploitation, we apply a conservative value penalty to imagination-based rollouts, preventing the policy from exploiting model inaccuracies while maintaining robust adaptation. Extensive evaluations demonstrate that our method outperforms state-of-the-art approaches, with superior stability and generalization under out-of-distribution and sparse-reward settings.","short_abstract":"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, a...","url_abs":"https://arxiv.org/abs/2606.00780","url_pdf":"https://arxiv.org/pdf/2606.00780v1","authors":"[\"Fuyuan Qian\",\"Menglong Zhang\",\"Song Wang\",\"Quanying Liu\"]","published":"2026-05-30T15:53:03Z","proceeding":"cs.LG","tasks":"[\"cs.LG\",\"cs.AI\"]","methods":"[\"Reinforcement Learning\",\"Transformer\"]","has_code":false}