Enregistré dans:
Détails bibliographiques
Auteurs principaux: Nesterova, Maria, Kolosov, Mikhail, Andreychuk, Anton, Cherepanov, Egor, Bulichev, Oleg, Kovalev, Alexey, Yakovlev, Konstantin, Panov, Aleksandr, Skrynnik, Alexey
Format: Preprint
Publié: 2026
Sujets:
Accès en ligne:https://arxiv.org/abs/2604.05943
Tags: Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
_version_ 1866910109193469952
author Nesterova, Maria
Kolosov, Mikhail
Andreychuk, Anton
Cherepanov, Egor
Bulichev, Oleg
Kovalev, Alexey
Yakovlev, Konstantin
Panov, Aleksandr
Skrynnik, Alexey
author_facet Nesterova, Maria
Kolosov, Mikhail
Andreychuk, Anton
Cherepanov, Egor
Bulichev, Oleg
Kovalev, Alexey
Yakovlev, Konstantin
Panov, Aleksandr
Skrynnik, Alexey
contents Recent advances in multi-agent reinforcement learning (MARL) have demonstrated success in numerous challenging domains and environments, but typically require specialized models for each task. In this work, we propose a coherent methodology that makes it possible for a single GPT-based model to learn and perform well across diverse MARL environments and tasks, including StarCraft Multi-Agent Challenge, Google Research Football and POGEMA. Our method, MARL-GPT, applies offline reinforcement learning to train at scale on the expert trajectories (400M for SMACv2, 100M for GRF, and 1B for POGEMA) combined with a single transformer-based observation encoder that requires no task-specific tuning. Experiments show that MARL-GPT achieves competitive performance compared to specialized baselines in all tested environments. Thus, our findings suggest that it is, indeed, possible to build a multi-task transformer-based model for a wide variety of (significantly different) multi-agent problems paving the way to the fundamental MARL model (akin to ChatGPT, Llama, Mistral etc. in natural language modeling).
format Preprint
id arxiv_https___arxiv_org_abs_2604_05943
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning
Nesterova, Maria
Kolosov, Mikhail
Andreychuk, Anton
Cherepanov, Egor
Bulichev, Oleg
Kovalev, Alexey
Yakovlev, Konstantin
Panov, Aleksandr
Skrynnik, Alexey
Artificial Intelligence
Recent advances in multi-agent reinforcement learning (MARL) have demonstrated success in numerous challenging domains and environments, but typically require specialized models for each task. In this work, we propose a coherent methodology that makes it possible for a single GPT-based model to learn and perform well across diverse MARL environments and tasks, including StarCraft Multi-Agent Challenge, Google Research Football and POGEMA. Our method, MARL-GPT, applies offline reinforcement learning to train at scale on the expert trajectories (400M for SMACv2, 100M for GRF, and 1B for POGEMA) combined with a single transformer-based observation encoder that requires no task-specific tuning. Experiments show that MARL-GPT achieves competitive performance compared to specialized baselines in all tested environments. Thus, our findings suggest that it is, indeed, possible to build a multi-task transformer-based model for a wide variety of (significantly different) multi-agent problems paving the way to the fundamental MARL model (akin to ChatGPT, Llama, Mistral etc. in natural language modeling).
title MARL-GPT: Foundation Model for Multi-Agent Reinforcement Learning
topic Artificial Intelligence
url https://arxiv.org/abs/2604.05943