用能量信号筛选轨迹，让扩散规划更稳定可靠。
Improving Diffusion Planners by Self-Supervised Action Gating with Energies
- 引入自监督能量机制，检测动作与环境动态的不一致性
- 在多个任务上显著提升扩散规划的性能和鲁棒性
- 无需重训练或环境交互，可无缝集成到现有流程
扩散规划是离线强化学习中一种强大的方法，但在价值引导选择时可能偏好得分高但与环境动态局部不一致的轨迹，导致执行脆弱。本文提出自监督动作门控能量（SAGE），一种推理阶段重排序方法，通过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，并构建用于短时程转移的动作条件潜在预测器。测试时，SAGE 根据潜在预测误差为每个候选轨迹分配能量值，并将此可行性得分与价值估计结合以选择动作。SAGE 可集成至支持轨迹采样和价值评分选动作的现有扩散规划流程中，无需环境回放或策略重训练。在运动、导航和操作基准上，SAGE 显著提升了扩散规划的性能与鲁棒性。
原文摘要 · Abstract (English)
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.
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。