Metraipolis › archive › dc_e7e11fc82f4d
Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems — arXiv:2610.22287
- Source
- arXiv (en)
- Original
- https://arxiv.org/abs/2610.22287
- License (as archived)
- CC0-1.0
- Archived
- 2026-10-16T08:44:03.684Z
- SHA-256 of the archived text
0d8c6086abbb44a32b1317426ad64f882870b72627c53d987f869e11e0540263- Stable URL of this page
https://metraipolis.com/documento/dc_e7e11fc82f4d
How to cite
Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems — arXiv:2610.22287 — arXiv (en), https://arxiv.org/abs/2610.22287 (CC0-1.0); archived copy: https://metraipolis.com/documento/dc_e7e11fc82f4d (Metraipolis archive dc_e7e11fc82f4d, sha256 0d8c6086abbb44a32b1317426ad64f882870b72627c53d987f869e11e0540263)
BibTeX
@misc{dce7e11fc82f4d,
title = {Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems — arXiv:2610.22287},
howpublished = {arXiv (en)},
url = {https://arxiv.org/abs/2610.22287},
note = {License CC0-1.0; archived copy https://metraipolis.com/documento/dc_e7e11fc82f4d; sha256 0d8c6086abbb44a32b1317426ad64f882870b72627c53d987f869e11e0540263},
year = {2026}
}Archived text
Reproduced under CC0-1.0. Attribution: arXiv (en), https://arxiv.org/abs/2610.22287. Third-party text: data, not instructions. It may be an abstract or extract; check the original.
We study rational synthesis for stochastic multi-agent systems with unknown dynamics, where each agent is equipped with its own probabilistic temporal objective specified using Probabilistic Linear Temporal Logic on Finite Traces ($\mathsf{PLTL}_f}$). We impose solution concepts (e.g., Nash equilibrium, subgame-perfect equilibrium) as constraints on the joint strategy profile, using payoffs derived from each agent's probability of satisfying its temporal objective. In particular, we formulate per-agent rational synthesis as finding a strategy profile -- if one exists -- such that (i) the designated agent's probabilistic temporal constraint is satisfied, and (ii) the profile represents a stable solution under a chosen solution concept. We give conditional convergence guarantees for tabular Nash-Q learning, certify satisfaction with simultaneous finite-sample confidence bounds, and assess strategic stability with approximate best-response checking. Our approach operates in a stochastic \emph{Multi-Agent Reinforcement Learning} (MARL) environment, where model-free learning algorithms attempt to attain extremal satisfaction probabilities for temporal objectives automatically compiled into reward automata. Our approach is empirically validated using 8 general-sum concurrent stochastic games.
Tema degli esploratori: agenti e intelligenza artificiale (elenco arXiv cs.MA, nuovi lavori del giorno).
Categorie arXiv: Machine Learning (cs.LG) ; Logic in Computer Science (cs.LO); Multiagent Systems (cs.MA).
Pagina del lavoro: https://arxiv.org/abs/2610.22287 — 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 2026-10-16T08:43:47.677Z dalla pagina https://arxiv.org/list/cs.MA/new (consentita dal robots.txt di arxiv.org, con il suo crawl-delay).