外观
论文arXiv 2609.241451 个月前
MimicAgent：通过 Prompt-to-Trajectory 生成学习四足技能
原文链接：MimicAgent: Quadruped Skills via Prompt-to-Trajectory Generation（arXiv 2609.24145 · 发布日期：2026-09-21）
MimicAgent: Quadruped Skills via Prompt-to-Trajectory Generation
MimicAgent将技能提示转为四足参考轨迹，用示例引导RL训练动态技能策略，并在仿真与真实世界部署验证。
核心要点
- 动机：四足奖励塑形难以调参，LLM自动设计奖励也难泛化到多技能和形态。
- 方法：给定技能提示，利用编码智能体生成粗略四足参考轨迹。
- 训练：将参考轨迹用于示例引导RL，得到可在仿真和真实世界部署的策略。
- 结果：在该智能体框架中提示Claude Fable 5.1，87%提示生成语义对齐轨迹。
验证范围与局限：验证范围为仿真和真实世界部署，摘要未说明具体机器人或任务细节。
英文摘要 (Abstract)
We present MimicAgent, a prompt-to-trajectory generation framework for learning dynamic quadruped skills. Although reward shaping is extensively used when training quadruped policies, navigating the resulting reward landscape is notoriously difficult, requiring hours of "graduate student descent". Eureka attempts to automate reward design with LLMs, but we find that it struggles to generalize across diverse skills and morphologies. Our key observation is that it is far easier for a human - and by association, an LLM - to generate reference motions than to shape reward functions. Our hypothesis is motivated by the success of example-guided RL for humanoids, which exploits large-scale motion capture datasets as references for training locomotion policies. Unlike humanoids, quadrupeds lack such reference motion data. Towards this end, we propose MimicAgent, an agentic harness that, given a skill prompt, generates quadruped reference trajectories with coding agents. These coarse reference trajectories are then used to train example-guided RL policies that are deployable in simulation and in the real-world. Notably, we find that when prompting Claude Fable 5.1 within our agentic harness, 87% of prompts yield semantically aligned reference trajectories.
作者：Lucky Kant Nayak, Narayanan Palghat Parameswaran, Neehar Peri, Deva Ramanan
来源
本页事实对应的公开页面，以原文为准。