arXiv cs.MA· Omar Adalat, Edwin Hamel-De le Court, Francesco Belardinelli·· 2 天前AI 评分20
多智能体系统中时序目标的理性策略学习
Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems
AI 导读
研究针对动态未知的随机多智能体系统，提出将每个智能体的概率时序目标（用 PLTL_f 描述）转化为奖励自动机，并在 Nash 均衡、子博弈完美均衡等解概念约束下求解理性综合问题。方法基于表格型 Nash-Q 学习，给出条件收敛保证，并用同时有限样本置信界验证满足性、以近似最佳响应检查评估策略稳定性。在 8 个一般和并发随机博弈上完成实证验证。
正文 · 原文
Abstract: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.
| Subjects: | Machine Learning (cs.LG); Logic in Computer Science (cs.LO); Multiagent Systems (cs.MA) |
| Cite as: | arXiv:2610.22287 [cs.LG] |
| (or arXiv:2610.22287v1 [cs.LG] for this version) | |
| https://doi.org/10.48550/arXiv.2610.22287 arXiv-issued DOI via DataCite (pending registration) |
Submission history
From: Omar Adalat [view email]
[v1]
Thu, 15 Oct 2026 17:42:52 UTC (4,685 KB)
来源：arXiv cs.MA · arxiv.org