{"ID":2841711,"CreatedAt":"2026-06-01T04:54:23.091178241Z","UpdatedAt":"2026-06-01T04:54:23.091178241Z","DeletedAt":null,"paper_url":"https://arxiv.org/abs/2511.11282","arxiv_id":"2511.11282","title":"ε-Optimally Solving Two-Player Zero-Sum POSGs","abstract":"We present a novel framework for ε-optimally solving two-player zero-sum partially observable stochastic games (zs-POSGs). These games pose a major challenge due to the absence of a principled connection with dynamic programming (DP) techniques developed for two-player zero-sum stochastic games (zs-SGs). Prior attempts at transferring solution methods have lacked a lossless reduction, defined here as a transformation that preserves value functions, equilibrium strategies, and optimality structure, thereby limiting generalisation to ad-hoc algorithms. This work introduces the first lossless reduction from zs-POSGs to transition-independent zs-SGs, enabling the principled application of a broad class of DP-based methods. We show empirically that point-based value iteration (PBVI) algorithms, applied via this reduction, produce ε-optimal strategies across a range of benchmark domains, consistently matching or outperforming existing state-of-the-art methods. Our results open a systematic pathway for algorithmic and theoretical transfer from SGs to partially observable settings.","short_abstract":"We present a novel framework for ε-optimally solving two-player zero-sum partially observable stochastic games (zs-POSGs). These games pose a major challenge due to the absence of a principled connection with dynamic programming (DP) techniques developed for two-player zero-sum stochastic games (zs-SGs). Prior attempts...","url_abs":"https://arxiv.org/abs/2511.11282","url_pdf":"https://arxiv.org/pdf/2511.11282v1","authors":"[\"Erwan Christian Escudie\",\"Matthia Sabatelli\",\"Olivier Buffet\",\"Jilles Steeve Dibangoye\"]","published":"2025-11-14T13:17:46Z","proceeding":"cs.GT","tasks":"[\"cs.GT\"]","methods":"[]","has_code":false}