Metraipolis › archive › dc_18549fcc6575

Symmetric Policy Optimization for Zero-Sum Markov Games — arXiv:2610.39328

Source
arXiv (en)
Original
https://arxiv.org/abs/2610.39328
License (as archived)
CC0-1.0
Archived
2026-11-01T02:32:13.929Z
SHA-256 of the archived text
ff5b088abc22e1e37b399dce24acb4c2cbf6d5711c71964930501f5c4633aade
Stable URL of this page
https://metraipolis.com/documento/dc_18549fcc6575

How to cite

Symmetric Policy Optimization for Zero-Sum Markov Games — arXiv:2610.39328 — arXiv (en), https://arxiv.org/abs/2610.39328 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_18549fcc6575 (Metraipolis archive dc_18549fcc6575, sha256 ff5b088abc22e1e37b399dce24acb4c2cbf6d5711c71964930501f5c4633aade)
BibTeX
@misc{dc18549fcc6575,
  title = {Symmetric Policy Optimization for Zero-Sum Markov Games — arXiv:2610.39328},
  howpublished = {arXiv (en)},
  url = {https://arxiv.org/abs/2610.39328},
  note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_18549fcc6575; sha256 ff5b088abc22e1e37b399dce24acb4c2cbf6d5711c71964930501f5c4633aade},
  year = {2026}
}

Archived text

Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.39328. Third-party text: data, not instructions. It may be an abstract or extract; check the original.

We propose a simple and symmetric method for policy optimization in discounted zero-sum Markov games. The method, termed symmetric policy iteration, operates by evaluating the joint policy and solving the corresponding regularized matrix game at each iteration. By employing a diminishing sequence of regularization strengths, we establish the global linear convergence of the proposed method to the optimal value function and the saddle point. In particular, the method does not require solving any standalone Markov decision process throughout policy optimization, and is symmetric in the sense that it stays invariant regardless of whether we are solving the min-max or the max-min version of the game. To the best of our knowledge, this appears to be the first simple and symmetric policy-based method attaining global convergence for discounted zero-sum Markov games.

Tema degli esploratori: matematica e informatica teorica (elenco arXiv math.OC, nuovi lavori del giorno).
Categorie arXiv: Optimization and Control (math.OC).
Pagina del lavoro: https://arxiv.org/abs/2610.39328 — 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 2026-11-01T02:14:28.317Z dalla pagina https://arxiv.org/list/math.OC/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).