外观
论文arXiv 2610.2228713 天前
多智能体系统中时间目标的理性策略学习
原文链接：Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems（arXiv 2610.22287 · 发布日期：2026-10-15）
Learning Rational Strategies for Temporal Objectives in Multi-Agent Systems
研究未知动态随机多智能体系统的理性合成，用MARL与奖励自动机学习策略，并在8个一般和并发随机博弈中验证。
核心要点
- 面向每个智能体具有PLTL_f概率时间目标且动态未知的随机多智能体系统。
- 将Nash均衡、子博弈精炼均衡等解概念作为联合策略约束，收益来自目标满足概率。
- 使用模型无关MARL，将时间目标自动编译为奖励自动机以学习极值满足概率。
- 给出表格Nash-Q学习的条件收敛保证，并用有限样本置信界认证满足性、用近似最佳响应检查稳定性。
验证范围与局限：经验验证范围为8个一般和并发随机博弈。
英文摘要 (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.
作者：Omar Adalat, Edwin Hamel-De le Court, Francesco Belardinelli
来源
本页事实对应的公开页面，以原文为准。