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

arXiv: https://arxiv.org/abs/2603.11346 · HTML: https://mlsanity.com/paper/2603.11346/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 30 of its 37 references that are in the map.
- First posted on arXiv 11 Mar 2026.

## Builds on (most cited first, 30 of 30)

- [Proximal Policy Optimization Algorithms](https://mlsanity.com/paper/1707.06347/) (2017)
- [DistilBERT, a distilled version of BERT: smaller, faster, cheaper and lighter](https://mlsanity.com/paper/1910.01108/) (2019)
- [Expressive Body Capture: 3D Hands, Face, and Body from a Single Image](https://mlsanity.com/paper/1904.05866/) (2019)
- [AMASS: Archive of Motion Capture as Surface Shapes](https://mlsanity.com/paper/1904.03278/) (2019)
- [Human Motion Diffusion Model](https://mlsanity.com/paper/2209.14916/) (2022)
- [The Surprising Effectiveness of PPO in Cooperative, Multi-Agent Games](https://mlsanity.com/paper/2103.01955/) (2021)
- [PhysDiff: Physics-Guided Human Motion Diffusion Model](https://mlsanity.com/paper/2212.02500/) (2022)
- [Human Motion Diffusion as a Generative Prior](https://mlsanity.com/paper/2303.01418/) (2023)
- [Perpetual Humanoid Control for Real-time Simulated Avatars](https://mlsanity.com/paper/2305.06456/) (2023)
- [InterGen: Diffusion-based Multi-human Motion Generation under Complex Interactions](https://mlsanity.com/paper/2304.05684/) (2023)
- [Emergent Complexity via Multi-Agent Competition](https://mlsanity.com/paper/1710.03748/) (2017)
- [MaskedMimic: Unified Physics-Based Character Control Through Masked Motion Inpainting](https://mlsanity.com/paper/2409.14393/) (2024)
- [SimPoE: Simulated Character Control for 3D Human Pose Estimation](https://mlsanity.com/paper/2104.00683/) (2021)
- [Inter-X: Towards Versatile Human-Human Interaction Analysis](https://mlsanity.com/paper/2312.16051/) (2023)
- [Neural probabilistic motor primitives for humanoid control](https://mlsanity.com/paper/1811.11711/) (2018)
- [Humanoid Parkour Learning](https://mlsanity.com/paper/2406.10759/) (2024)
- [HOVER: Versatile Neural Whole-Body Controller for Humanoid Robots](https://mlsanity.com/paper/2410.21229/) (2024)
- [ExBody2: Advanced Expressive Humanoid Whole-Body Control](https://mlsanity.com/paper/2412.13196/) (2024)
- [GMT: General Motion Tracking for Humanoid Whole-Body Control](https://mlsanity.com/paper/2506.14770/) (2025)
- [ActFormer: A GAN-based Transformer towards General Action-Conditioned 3D Human Motion Generation](https://mlsanity.com/paper/2203.07706/) (2022)
- [InterMimic: Towards Universal Whole-Body Control for Physics-Based Human-Object Interactions](https://mlsanity.com/paper/2502.20390/) (2025)
- [ReGenNet: Towards Human Action-Reaction Synthesis](https://mlsanity.com/paper/2403.11882/) (2024)
- [CooHOI: Learning Cooperative Human-Object Interaction with Manipulated Object Dynamics](https://mlsanity.com/paper/2406.14558/) (2024)
- [Interaction Transformer for Human Reaction Generation](https://mlsanity.com/paper/2207.01685/) (2022)
- [ResMimic: From General Motion Tracking to Humanoid Whole-body Loco-Manipulation via Residual Learning](https://mlsanity.com/paper/2510.05070/) (2025)
- [Track Any Motions under Any Disturbances](https://mlsanity.com/paper/2509.13833/) (2025)
- [PARC: Physics-based Augmentation with Reinforcement Learning for Character Controllers](https://mlsanity.com/paper/2505.04002/) (2025)
- [Towards Immersive Human-X Interaction: A Real-Time Framework for Physically Plausible Motion Synthesis](https://mlsanity.com/paper/2508.02106/) (2025)
- [PhysReaction: Physically Plausible Real-Time Humanoid Reaction Synthesis via Forward Dynamics Guided 4D Imitation](https://mlsanity.com/paper/2404.01081/) (2024)
- [HHI-Assist: A Dataset and Benchmark of Human-Human Interaction in Physical Assistance Scenario](https://mlsanity.com/paper/2509.10096/) (2025)

## Built on by (most cited first, 1 of 1)

- [From Digital Human Interactions to Physics-Based Humanoid Skills: Physics-Grounded Post-Training of Interaction Generators](https://mlsanity.com/paper/2610.10322/) (2026)

## Abstract (arXiv)

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.