Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning

• URL: http://arxiv.org/abs/2605.22748v1
• Date: Thu, 21 May 2026 17:15:54 GMT
• Title: Superhuman Safe and Agile Racing through Multi-Agent Reinforcement Learning
• Abstract summary: We show that multi-agent reinforcement learning provides the safety scaffolding required for real-world interaction.<n>We train agents to navigate complex aerodynamic interactions and strategic maneuvering with a variable number of racers.<n>Our agents outperform reducing collision rates by 50 % compared to state-of-the-art single-agent baselines.
• Score: 22.65712097455206
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: Autonomous systems have achieved superhuman performance in isolation or simulation, yet they remain brittle in shared, dynamic real-world spaces. This failure stems from the dominant single-agent paradigm for physical applications, where other actors are ignored or treated as environmental noise, preventing effective coordination. Here we show that multi-agent reinforcement learning provides the essential safety scaffolding required for real-world interaction. Using high-speed quadrotor racing as a high-stakes testbed, we train agents to navigate complex aerodynamic interactions and strategic maneuvering with a variable number of racers. Through league-based self-play, agents evolve sophisticated anticipatory behaviors, including proactive collision avoidance, overtaking, and handling multi-agent physical interactions, including aerodynamic downwash. Our agents outperform a champion-level human pilot in multi-player races at speeds exceeding 22 m/s, while simultaneously reducing collision rates by 50 % compared to state-of-the-art single-agent baselines. Crucially, training with diverse artificial agents enables zero-shot generalization to safer human interaction. These results suggest that the path to robust robotic co-existence lies not in isolated safety constraints, but in the rigorous demands of multi-agent interaction. Multimedia materials are available at: https://rpg.ifi.uzh.ch/marl

Related papers

• Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players [87.87842088508553]
  We present our generative multi-agent world model for interactive simulation.<n>Our model improves video fidelity, action controllability, and inter-agent consistency over slot-based and dense-attention baselines.
  arXiv  Detail & Related papers  (2026-05-27T17:59:31Z)
• RPG: Robust Policy Gating for Smooth Multi-Skill Transitions in Humanoid Fighting [52.18271301977709]
  We propose RPG, a hybrid expert policy framework, for smooth and stable humanoid multi-skills transition.<n>Our approach incorporates motion transition randomization and temporal randomization to train a unified policy that generates agile fighting actions.<n>We design a control pipeline that integrates walking/running locomotion with fighting skills, allowing humanlike long-time combat of arbitrary duration.
  arXiv  Detail & Related papers  (2026-04-23T07:14:35Z)
• RoboStriker: Hierarchical Decision-Making for Autonomous Humanoid Boxing [43.240817529539356]
  RoboStriker is a hierarchical three-stage framework that enables fully autonomous humanoid boxing.<n>The framework first learns a comprehensive repertoire of boxing skills by training a single-agent motion tracker on human motion capture data.<n>In the final stage, we introduce Latent-Space Neural Fictitious Self-Play (LS-NFSP), where competing agents learn competitive tactics by interacting within the latent action space.
  arXiv  Detail & Related papers  (2026-01-30T03:51:58Z)
• Diffusion Forcing for Multi-Agent Interaction Sequence Modeling [52.769202433667125]
  MAGNet is a unified autoregressive diffusion framework for multi-agent motion generation.<n>It supports a wide range of interaction tasks through flexible conditioning and sampling.<n>It captures both tightly synchronized activities and loosely structured social interactions.
  arXiv  Detail & Related papers  (2025-12-19T18:59:02Z)
• Agile Flight Emerges from Multi-Agent Competitive Racing [7.9331622838838305]
  We find that both agile flight and strategy emerge from agents trained with reinforcement learning.<n>We find that multi-agent competition yields policies that transfer more reliably to the real world than policies trained with a single-agent progress-based reward.
  arXiv  Detail & Related papers  (2025-12-12T18:48:50Z)
• InterAgent: Physics-based Multi-agent Command Execution via Diffusion on Interaction Graphs [72.5651722107621]
  InterAgent is an end-to-end framework for text-driven physics-based multi-agent humanoid control.<n>We introduce an autoregressive diffusion transformer equipped with multi-stream blocks, which decouples proprioception, exteroception, and action to cross-modal interference.<n>We also propose a novel interaction graph exteroception representation that explicitly captures fine-grained joint-to-joint spatial dependencies.
  arXiv  Detail & Related papers  (2025-12-08T10:46:01Z)
• Human-compatible driving partners through data-regularized self-play reinforcement learning [3.9682126792844583]
  Human-Regularized PPO (HR-PPO) is a multi-agent algorithm where agents are trained through self-play with a small penalty for deviating from a human reference policy. Results show our HR-PPO agents are highly effective in achieving goals, with a success rate of 93%, an off-road rate of 3.5%, and a collision rate of 3%.
  arXiv  Detail & Related papers  (2024-03-28T17:56:56Z)
• ProAgent: Building Proactive Cooperative Agents with Large Language Models [89.53040828210945]
  ProAgent is a novel framework that harnesses large language models to create proactive agents. ProAgent can analyze the present state, and infer the intentions of teammates from observations. ProAgent exhibits a high degree of modularity and interpretability, making it easily integrated into various coordination scenarios.
  arXiv  Detail & Related papers  (2023-08-22T10:36:56Z)
• Learning Agile Soccer Skills for a Bipedal Robot with Deep Reinforcement Learning [26.13655448415553]
  Deep Reinforcement Learning (Deep RL) is able to synthesize sophisticated and safe movement skills for a low-cost, miniature humanoid robot. We used Deep RL to train a humanoid robot with 20 actuated joints to play a simplified one-versus-one (1v1) soccer game. The resulting agent exhibits robust and dynamic movement skills such as rapid fall recovery, walking, turning, kicking and more.
  arXiv  Detail & Related papers  (2023-04-26T16:25:54Z)
• Multi-Agent Interplay in a Competitive Survival Environment [0.0]
  This thesis is part of the author's thesis "Multi-Agent Interplay in a Competitive Survival Environment" for the Master's Degree in Artificial Intelligence and Robotics at Sapienza University of Rome, 2022.
  arXiv  Detail & Related papers  (2023-01-19T12:04:03Z)
• Scalable Task-Driven Robotic Swarm Control via Collision Avoidance and Learning Mean-Field Control [23.494528616672024]
  We use state-of-the-art mean-field control techniques to convert many-agent swarm control into classical single-agent control of distributions. Here, we combine collision avoidance and learning of mean-field control into a unified framework for tractably designing intelligent robotic swarm behavior.
  arXiv  Detail & Related papers  (2022-09-15T16:15:04Z)
• Learning Latent Representations to Influence Multi-Agent Interaction [65.44092264843538]
  We propose a reinforcement learning-based framework for learning latent representations of an agent's policy. We show that our approach outperforms the alternatives and learns to influence the other agent.
  arXiv  Detail & Related papers  (2020-11-12T19:04:26Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.