通过自监督动作能量门控改进扩散规划器
Improving Diffusion Planners by Self-Supervised Action Gating with Energies
AI总结：
提出SAGE方法，利用潜在一致性信号在推理时重新排序轨迹，惩罚动态不一致的计划，从而提升扩散规划器的性能和鲁棒性。
摘要：
扩散规划器是离线强化学习的一种强大方法，但当价值引导选择偏好得分高但局部与环境动态不一致的轨迹时，它们可能会失败，导致执行脆弱。我们提出了自监督动作能量门控（SAGE），一种推理时重排序方法，使用潜在一致性信号惩罚动态不一致的计划。SAGE在离线状态序列上训练联合嵌入预测架构（JEPA）编码器，并训练一个动作条件的潜在预测器用于短时域过渡。在测试时，SAGE为每个采样候选分配一个由其潜在预测误差给出的能量，并将此可行性得分与价值估计相结合以选择动作。SAGE可以集成到现有的扩散规划流程中，这些流程可以通过价值评分采样轨迹和选择动作；它不需要环境回滚，也不需要重新训练策略。在运动、导航和操作基准测试中，SAGE提高了扩散规划器的性能和鲁棒性。
英文摘要：
Diffusion planners are a strong approach for offline reinforcement learning, but they can fail when value-guided selection favours trajectories that score well yet are locally inconsistent with the environment dynamics, resulting in brittle execution. We propose Self-supervised Action Gating with Energies (SAGE), an inference-time re-ranking method that penalises dynamically inconsistent plans using a latent consistency signal. SAGE trains a Joint-Embedding Predictive Architecture (JEPA) encoder on offline state sequences and an action-conditioned latent predictor for short horizon transitions. At test time, SAGE assigns each sampled candidate an energy given by its latent prediction error and combines this feasibility score with value estimates to select actions. SAGE can integrate into existing diffusion planning pipelines that can sample trajectories and select actions via value scoring; it requires no environment rollouts and no policy re-training. Across locomotion, navigation, and manipulation benchmarks, SAGE improves the performance and robustness of diffusion planners.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
