关键区间均方误差：迈向机器人操作策略的可靠离线验证
Critical Interval MSE: Toward Reliable Offline Validation for Robot Manipulation Policies
AI总结：
提出关键区间均方误差（CI-MSE），通过限制误差计算到任务关键段并配合动作对齐，显著提升验证误差与真实性能的相关性，加速策略迭代。
摘要：
真实世界评估是机器人策略的黄金标准，因为它能在物理条件和部署挑战下测试策略。然而，真实世界评估也是迭代机器人策略的瓶颈：成本高、难以复现，且通常过于稀疏而无法可靠比较相近模型变体。一个直接的性能代理是专家演示上的验证损失，但该代理通常与真实世界性能相关性差。本文提出关键区间均方误差（CI-MSE），一种直观简单且有效的离线验证指标。CI-MSE将误差计算限制在任务关键段，并结合简单的动作对齐过程以更好地匹配 rollout 时的行为。在仿真和真实世界实验中，CI-MSE在验证误差与 rollout 性能之间产生了比原始MSE更强的相关性。在广泛策略检查点上，CI-MSE的斯皮尔曼秩相关系数为-0.87，比原始MSE的-0.61更接近理想值-1，显示出显著改进。通过敏感性分析，我们证明该指标对广泛的超参数具有鲁棒性。我们进一步研究了CI-MSE在评估分布偏移下的有效性，并提出了使用该指标时的设计边界。总之，本文提供了一种简单可靠的离线验证工具，用于加速策略迭代。项目网页：https://ci-mse.github.io/
英文摘要：
Real-world evaluation is the gold standard for robot manipulation policies because it tests them against the physical conditions and deployment challenges they are ultimately designed to handle. However, real-world evaluation is also the bottleneck for iterating on robot imitation learning policies: it is costly, difficult to reproduce, and often too sparse to reliably compare nearby model variants. A straightforward proxy for performance is validation loss on expert demonstrations, but this proxy is often poorly correlated with real-world performance. In this paper, we introduce Critical Interval MSE (CI-MSE), an intuitively simple yet effective offline validation metric. CI-MSE uses a zero-shot agent to localize task-critical segments, restricts error computation to those segments, and applies simple action-alignment procedures that better match rollout-time behavior. Across simulation and real-world experiments, CI-MSE generally yields a stronger correlation between validation error and rollout performance than raw MSE. Across 27 distinct policy checkpoints, CI-MSE achieves a Spearman rank correlation of $-0.87$, closer to the ideal value of $-1$ than raw MSE's $-0.61$, demonstrating a significant improvement. Sensitivity analysis shows that our metric is robust across a wide range of hyperparameter settings. We further study the effectiveness of CI-MSE under evaluation distribution shifts and identify practical boundaries for its use. In summary, this paper provides a simple and reliable offline validation tool for accelerating policy iteration. Project webpage: https://ci-mse.github.io/
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。
