论文/arXiv 2610.07056·23 天前

行为克隆之谜

提出OCBench，用类人示教的可控脚本策略，在机器人操作基准中复现并研究行为克隆异常现象。

AI 整理

• 本体 SDK 与控制
• 仿真与训练
• 数据与采集

原文链接：Behavioral Cloning Mystery（arXiv 2610.07056 · 发布日期：2026-10-05）

Behavioral Cloning Mystery

提出OCBench，用类人示教的可控脚本策略，在机器人操作基准中复现并研究行为克隆异常现象。

核心要点

• 行为克隆在现实中常出现反直觉现象，但真实实验昂贵且不可控，仿真合成数据也不易观察。
• OCBench提供机器人操作基准，包含可控脚本策略，并模拟人类示教的关键属性。
• 实验表明，OCBench能在受控设置中复现多种已被报道的行为克隆相关现象。
• 借助GPU加速环境和脚本策略，OCBench支持分析并反驳关于这些现象的不同假设，并提供项目页面。

验证范围与局限：验证范围为OCBench的GPU加速环境、脚本策略和机器人操作基准中的受控设置。

英文摘要 (Abstract)

Behavioral cloning (BC), despite its simplicity, exhibits many counterintuitive phenomena in the real world. For example, the performance of BC often keeps increasing as the model overfits more to the dataset, and fully closed-loop policies often completely fail without action chunking. Unfortunately, properly studying these anecdotal phenomena ("behavioral cloning mysteries") is challenging: in the real world, datasets and experiments are costly and not fully controllable; in simulation with synthetic data, these phenomena are often not easily observed partly due to the discrepancy between scripted policies and human demonstrations. In this work, we propose OCBench, a robotic manipulation benchmark with controllable scripted policies that have similar properties to human demonstrations. We show that, by mimicking key properties of human demonstrations, OCBench reproduces many anecdotal BC-related phenomena in controlled settings. With its GPU-accelerated environments and scripted policies, we demonstrate how OCBench enables scientific studies of previously reported BC-related phenomena by analyzing and refuting various hypotheses. Project page: https://seohong.me/projects/ocbench

作者：Seohong Park, Sergey Levine

来源

本页事实对应的公开页面，以原文为准。

1. arXiv 2610.07056：Behavioral Cloning Mystery访问 2026-10-21