Does Imitation Learning Preserve Temporal Robustness in Dexterous Manipulation? An Expert-Learner Comparison Across Task Execution Speeds

• 类型：arxiv
• 标识：2609.01453
• 链接：https://arxiv.org/abs/2609.01453
• 主分类：evaluation
• 形态：method
• TLDR：Dexterous manipulation policies learned by imitation are typically evaluated for robustness to variation in scenes, objects, or instructions, but their performance across task execution speeds is less often examined. This leaves open how much temporal robustness a learner retains relative to the expert it imitates. We compare an expert and learner under the same task conditions, initial-condition draws, and speedup factors. We instantiate the evaluation in ParcelStow, a contact-rich task in which the robot acquires, reorients, and inserts a parcel. The demonstrations span the speedup range for
• 待LLM分类：否
• 标题中文：模仿学习是否保留灵巧操作的时间鲁棒性？跨任务执行速度的专家-学习者对比
• TLDR中文：模仿学习得到的灵巧操作策略通常在场景、物体或指令变化的鲁棒性上得到评估，但在不同任务执行速度下的表现则较少被考察。这留下了一个开放问题：相对于其模仿的专家，学习者保留了多少时间鲁棒性。我们在相同的任务条件、初始状态采样与加速因子下对比专家与学习者。评测任务实例化为 ParcelStow，一个接触丰富的任务，机器人需要抓取、重定向并插入包裹。演示覆盖了该任务的加速范围
• 来源文件：
• /inbox/tom/_candidates/2026-09-03-agent-rag-longcontext-candidates.json