学习辅助：基于多智能体强化学习的物理接地人-人控制
Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning
把「双人近距离施力交互」的运动模仿建模为多智能体 RL，并用单人运动跟踪控制器初始化伙伴策略、动态重定向参考动作——这套「先单人预训练再双人协同」的流程可直接迁移到视觉驱动的虚拟人/数字人交互合成与具身人形控制任务。
原文依据 we formulate the imitation of closely interacting, force-exchanging human-human motion sequences as a multi-agent reinforcement learning problem
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论人形机器人有潜力深刻改变日常服务与照护应用。尽管近期在物理引擎内的一般运动跟踪（GMT）方面的进展已使虚拟角色和人形机器人能够复现广泛的人体运动，但这些行为主要局限于无接触的社交互动或孤立动作。相比之下，辅助场景需要持续感知人类伙伴，并快速适应其不断变化的姿态与动力学。本文将紧密交互、存在力交换的人-人运动序列的模仿建模为一个多智能体强化学习问题。我们在物理仿真器中联合训练支持者（助手）智能体与受助者智能体的伙伴感知策略，以跟踪辅助运动参考。为使该问题可解，我们提出一种伙伴策略初始化方案，从单人运动跟踪控制器迁移先验，显著改善探索。我们进一步提出动态参考重定向与接触促进奖励，使助手的参考运动适配受助者的实时姿态，并鼓励物理上有意义的支撑。我们表明，\model 是首个在已有基准上成功跟踪辅助交互运动的方法，展示了多智能体强化学习建模对于物理接地且具社会意识的人形控制的优势。
英文原文摘要 1478 字符
Humanoid robotics has strong potential to transform daily service and caregiving applications. Although recent advances in general motion tracking within physics engines (GMT) have enabled virtual characters and humanoid robots to reproduce a broad range of human motions, these behaviors are primarily limited to contact-less social interactions or isolated movements. Assistive scenarios, by contrast, require continuous awareness of a human partner and rapid adaptation to their evolving posture and dynamics. In this paper, we formulate the imitation of closely interacting, force-exchanging human-human motion sequences as a multi-agent reinforcement learning problem. We jointly train partner-aware policies for both the supporter (assistant) agent and the recipient agent in a physics simulator to track assistive motion references. To make this problem tractable, we introduce a partner policies initialization scheme that transfers priors from single-human motion-tracking controllers, greatly improving exploration. We further propose dynamic reference retargeting and contact-promoting reward, which adapt the assistant's reference motion to the recipient's real-time pose and encourage physically meaningful support. We show that \model is the first method capable of successfully tracking assistive interaction motions on established benchmarks, demonstrating the benefits of a multi-agent RL formulation for physically grounded and socially aware humanoid control.