BriefGPT.xyz
Oct, 2024
随时约束的多智能体强化学习
Anytime-Constrained Multi-Agent Reinforcement Learning
HTML
PDF
Jeremy McMahan, Xiaojin Zhu
TL;DR
本研究针对多智能体环境中的随时约束问题,提出了随时约束均衡(ACE)的解决方案概念。研究提供了一个全面的随时约束马尔可夫游戏理论,包括可行策略的计算特征、ACE的固定参数可计算算法,以及近似计算可行ACE的多项式时间算法,显示出在最坏情况分析下,计算可行策略的近似保证是可能的最优解。
Abstract
We introduce
Anytime Constraints
to the
Multi-Agent
setting with the corresponding solution concept being anytime-constrained equilibrium (ACE). Then, we present a comprehensive theory of anytime-constrained
→