用测试时模型预测控制提升预训练轨迹模型的决策能力
M$^3$PC: Test-time Model Predictive Control for Pretrained Masked Trajectory Model
- 测试时引入模型预测控制，利用预训练模型自有的预测能力指导动作选择
- 在D4RL和RoboMimic上无需额外训练即显著提升性能
- 适用于离线到在线迁移与目标导向任务，支持在线交互与多目标泛化
近期离线强化学习研究显示，统一的Transformer在掩码自编码目标下能有效捕捉轨迹数据中状态、动作、奖励等模态间的关系。然而，推理阶段尚未充分利用该信息，此时代理需生成最优策略，而非仅重建被掩码的部分。鉴于预训练轨迹模型可通过不同掩码模式充当策略模型与世界模型，我们提出在测试时使用模型预测控制（MPC），以利用模型自身的预测能力指导动作选择。在D4RL和RoboMimic上的实验证明，该推理阶段的MPC显著提升了预训练轨迹模型的决策性能，且无需额外参数训练。此外，该框架可拓展至离线到在线（O2O）强化学习与目标达成任务，在提供额外在线交互预算时取得更显著性能提升，并在不同任务目标下展现更强泛化能力。代码已公开：https://github.com/wkh923/m3pc。
原文摘要 · Abstract (English)
Recent work in Offline Reinforcement Learning (RL) has shown that a unified Transformer trained under a masked auto-encoding objective can effectively capture the relationships between different modalities (e.g., states, actions, rewards) within given trajectory datasets. However, this information has not been fully exploited during the inference phase, where the agent needs to generate an optimal policy instead of just reconstructing masked components from unmasked ones. Given that a pretrained trajectory model can act as both a Policy Model and a World Model with appropriate mask patterns, we propose using Model Predictive Control (MPC) at test time to leverage the model's own predictive capability to guide its action selection. Empirical results on D4RL and RoboMimic show that our inference-phase MPC significantly improves the decision-making performance of a pretrained trajectory model without any additional parameter training. Furthermore, our framework can be adapted to Offline to Online (O2O) RL and Goal Reaching RL, resulting in more substantial performance gains when an additional online interaction budget is provided, and better generalization capabilities when different task targets are specified. Code is available: https://github.com/wkh923/m3pc.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。