Metraipolis › archive › dc_da41ed67d324
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games — arXiv:2609.01549
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2609.01549
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-17T06:52:26.232Z
- SHA-256 of the archived text
ac83ac9c427c6d6aad563a7038f5552f630544d8f8b5967f4a469c487dad06fe- Stable URL of this page
https://metraipolis.com/documento/dc_da41ed67d324
How to cite
NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games — arXiv:2609.01549 — arXiv (en), https://arxiv.org/abs/2609.01549 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_da41ed67d324 (Metraipolis archive dc_da41ed67d324, sha256 ac83ac9c427c6d6aad563a7038f5552f630544d8f8b5967f4a469c487dad06fe)
BibTeX
@misc{dcda41ed67d324,
title = {NashDreamer: Model-Based Reinforcement Learning for Zero-Sum Imperfect-Information Games — arXiv:2609.01549},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2609.01549},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_da41ed67d324; sha256 ac83ac9c427c6d6aad563a7038f5552f630544d8f8b5967f4a469c487dad06fe},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2609.01549. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
Model-based reinforcement learning (MBRL) has achieved remarkable results in single-agent domains, yet its extension to competitive imperfect information games (IIGs) remains underexplored. In multi-agent settings, opponent-induced non-stationarity complicates the learning process, and decentralized model learning faces severe identifiability barriers, which we argue make centralized model learning a mathematical necessity. Building on this analysis, we propose NashDreamer, a principled MBRL framework for two-player zero-sum IIGs. It introduces a centralized Multi-Agent Recurrent State-Space Model (MARSSM) that decouples environment dynamics from the effect of players' strategies on their individual observations. NashDreamer is designed to use arbitrary policy gradient algorithms and inherits their convergence guarantees towards Nash equilibria under an idealized model. Empirical evaluations across four benchmark games demonstrate that NashDreamer substantially improves sample efficiency over model-free baselines early in the training. Finally, we theoretically analyze the architecture's optimization landscape, identifying the vulnerability of the Dreamer family of algorithms to posterior collapse in stochastic environments. We leave it as an open challenge. Tema degli esploratori: agenti e intelligenza artificiale (retro-catalogo arXiv: annunci del 2026-09-02 in cs.LG). Categorie arXiv: Machine Learning (cs.LG). Pagina del lavoro: https://arxiv.org/abs/2609.01549 — autori e testo completo sono lì (qui omessi i nomi: nessun dato personale nel deposito). Licenza: titolo e abstract sono metadati arXiv distribuiti in CC0 1.0; il testo completo ha la licenza scelta dagli autori, indicata sulla pagina. Letto il 2026-10-17T06:41:55.866Z dalla pagina https://arxiv.org/catchup/cs.LG/2026-09-02?abs=True (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).