Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning

2026-03-11

AI Summary

This work addresses the challenge that existing virtual characters and humanoid robots struggle to simulate physically interactive assistance behaviors requiring continuous perception and dynamic adaptation. The authors formulate human-like close-contact force interactions as a multi-agent reinforcement learning problem, jointly training the policies of a supporter and a recipient in physical simulation to track a reference sequence of assistive motions. By introducing partner policy initialization, dynamic reference redirection, and a contact-aware reward mechanism, the approach achieves, for the first time, successful tracking of complex assistive interaction tasks, overcoming the limitations of single-agent methods. Experiments on standard benchmarks demonstrate the effectiveness of the proposed framework in embodied, socially aware humanoid control.

Technology Category

• Intelligent Robots: Human-Robot Interaction
• Humans and AI: Human-Aware Planning and Behavior Prediction
• Multiagent Systems: Adversarial Agents

Application Category

• User Modeling, Personalization and Recommendation: User modeling and simulation for interactive and conversational systems
• Responsible Web: Machine-in-the-loop, human agency and autonomy
• Semantics and Knowledge: Data modeling to support human-machine intelligence, including LLMs agents, intelligent system behavior, explanations, and user-friendly interactions

Abstract

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 AssistMimic 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.

Problem

• human-human interaction
• assistive motion
• multi-agent reinforcement learning
• physics-based simulation
• humanoid control

Innovation

• multi-agent reinforcement learning
• physics-grounded humanoid control
• assistive interaction
• dynamic reference retargeting
• contact-promoting reward