ARXIV:2603.11346 · HUMANOID ROBOTICS · SUBMITTED 02 APR · 02:30 UTC · FRESHNESS STALE

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

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

arXiv

AssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning.

Blocked on Code›Score5.0Evidence unverified

Opportunity summary

Pain AssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning.

Evidence 0 refs | 0 sources | 17% coverage

Blocker Evidence unverified

Open Build Read PDF Signal Canvas Track

PROBLEM

AssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning. Although recent advances in general motion tracking within physics engines (GMT) have enabled virtual characters and humanoid robots to reproduce a…

METHOD

Full 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.

RESULT

ScienceToStartup currently rates this 5.0/10 on the public viability pass. 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…

WHY NOW

Humanoid Robotics moved forward this cycle; last verified April 2026. Public score 5.0/10.

Continue into Read for claims, analysis, references, and neighboring papers.

Opportunity summary

Score5.0

PainAssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning.

Evidence0 refs | 0 sources | 17% coverage

Blockermissing authors

Analysis summary

AssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning.

VerifiedSource: PDF linkedPartialPaperPack: 3 of 4 citation fields filledMissingMissing fields: authorsPartialProof: unverified proof status

Competitive landscape

AssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning.

Segment

Humanoid Robotics

Adoption evidence

No public code link in the paper record yet

Commercial read

5.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

{ "contract_version": "paper-r2", "paper_id": "2ebf3f19-698e-407e-92a0-b0a937dc5b8f", "arxiv_id": "2603.11346", "canonical_route": "/paper/learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning", "active_tab": "synced from current hash by the drawer client", "selected_artifact": "learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning", "endpoints": { "paper_pack": "/api/v1/paper/learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning/paper-pack", "build_passport": "/api/v1/paper/learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning/build-passport", "mcp_resource": "sciencetostartup://surfaces/paper-workspace" } }

{ "surface": "paper", "mode": "paper", "query": "Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning", "normalized_query": "2603.11346", "route": "/paper/learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning", "paper_ref": "learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning", "topic_slug": null, "benchmark_ref": null, "dataset_ref": null }

{ "@context": "https://schema.org", "@graph": [ { "@type": "WebPage", "@id": "https://sciencetostartup.com/paper/learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning#webpage", "url": "https://sciencetostartup.com/paper/learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning", "name": "Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning", "description": "AssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning.", "isPartOf": { "@id": "https://sciencetostartup.com/#website" } }, { "@type": "ScholarlyArticle", "@id": "https://sciencetostartup.com/paper/learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning#scholarlyArticle", "headline": "Learning to Assist: Physics-Grounded Human-Human Control via Multi-Agent Reinforcement Learning", "description": "AssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning.", "url": "https://sciencetostartup.com/paper/learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning", "sameAs": "https://arxiv.org/abs/2603.11346", "identifier": { "@type": "PropertyValue", "propertyID": "arXiv", "value": "2603.11346" }, "isAccessibleForFree": true, "isPartOf": { "@id": "https://sciencetostartup.com/#website" }, "datePublished": "2026-03-11T22:25:44.000Z", "additionalProperty": [ { "@type": "PropertyValue", "propertyID": "viabilityScore", "value": 5 }, { "@type": "PropertyValue", "propertyID": "researchDomain", "value": "Humanoid Robotics" } ] }, { "@type": "BreadcrumbList", "itemListElement": [ { "@type": "ListItem", "position": 1, "name": "Home", "item": "https://sciencetostartup.com" }, { "@type": "ListItem", "position": 2, "name": "Humanoid Robotics", "item": "https://sciencetostartup.com/topics" }, { "@type": "ListItem", "position": 3, "name": "Learning to Assist: Physics-Grounded Human-Human Control via", "item": "https://sciencetostartup.com/paper/learning-to-assist-physics-grounded-human-human-control-via-multi-agent-reinforcement-learning" } ] } ] }

Competitive landscape

AssistMimic enables humanoid robots to adaptively assist humans through advanced multi-agent reinforcement learning.

Segment

Humanoid Robotics

Adoption evidence

No public code link in the paper record yet

Commercial read

5.0/10 public viability

Direct

not classified

Adjacent

not classified

Substitute

not classified

Unknown

not classified

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

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

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline

Claim map

Constellation map

Competitive landscape

Buzz

PDF

REFERENCES

Related Papers

Related Resources

Subscribe to the weekly brief

Build artifacts

Brief

Experiment plan

Validation checklist

Scientific founder

Translational engineer

Domain operator

GTM lead

Regulatory/clinical advisor

Timeline