Agile Flight Emerges from Multi-Agent Competitive Racing

Fuente: arXiv
Guardado en:
Detalles Bibliográficos
Autores principales: Pasumarti, Vineet, Bianchi, Lorenzo, Loquercio, Antonio
Formato: Preprint
Publicado: 2025
Materias:
Acceso en línea:
Etiquetas: Agregar Etiqueta
Sin Etiquetas, Sea el primero en etiquetar este registro!
_version_ 1866911483373289472
author Pasumarti, Vineet
Bianchi, Lorenzo
Loquercio, Antonio
author_facet Pasumarti, Vineet
Bianchi, Lorenzo
Loquercio, Antonio
contents Through multi-agent competition and the sparse high-level objective of winning a race, we find that both agile flight (e.g., high-speed motion pushing the platform to its physical limits) and strategy (e.g., overtaking or blocking) emerge from agents trained with reinforcement learning. We provide evidence in both simulation and the real world that this approach outperforms the common paradigm of training agents in isolation with rewards that prescribe behavior, e.g., progress on the raceline, in particular when the complexity of the environment increases, e.g., in the presence of obstacles. Moreover, 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, despite the two methods using the same simulation environment, randomization strategy, and hardware. In addition to improved sim-to-real transfer, the multi-agent policies also exhibit some degree of generalization to opponents unseen at training time. Overall, our work, following in the tradition of multi-agent competitive game-play in digital domains, shows that sparse task-level rewards are sufficient for training agents capable of advanced low-level control in the physical world. Code: https://github.com/Jirl-upenn/AgileFlight_MultiAgent
format Preprint
id arxiv_https___arxiv_org_abs_2512_11781
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Agile Flight Emerges from Multi-Agent Competitive Racing
Pasumarti, Vineet
Bianchi, Lorenzo
Loquercio, Antonio
Robotics
Artificial Intelligence
Multiagent Systems
Through multi-agent competition and the sparse high-level objective of winning a race, we find that both agile flight (e.g., high-speed motion pushing the platform to its physical limits) and strategy (e.g., overtaking or blocking) emerge from agents trained with reinforcement learning. We provide evidence in both simulation and the real world that this approach outperforms the common paradigm of training agents in isolation with rewards that prescribe behavior, e.g., progress on the raceline, in particular when the complexity of the environment increases, e.g., in the presence of obstacles. Moreover, 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, despite the two methods using the same simulation environment, randomization strategy, and hardware. In addition to improved sim-to-real transfer, the multi-agent policies also exhibit some degree of generalization to opponents unseen at training time. Overall, our work, following in the tradition of multi-agent competitive game-play in digital domains, shows that sparse task-level rewards are sufficient for training agents capable of advanced low-level control in the physical world. Code: https://github.com/Jirl-upenn/AgileFlight_MultiAgent
title Agile Flight Emerges from Multi-Agent Competitive Racing
topic Robotics
Artificial Intelligence
Multiagent Systems
url https://arxiv.org/abs/2512.11781