将多智能体覆盖问题转为可高效求解的博弈模型，提升训练与执行速度。
Learning Closed-Loop Parametric Nash Equilibria of Multi-Agent Collaborative Field Coverage
- 将覆盖任务建模为潜在博弈，转化为单目标控制问题
- 训练速度比基线快10倍，策略执行收敛更快
- 适合工程中需要快速协同的多机器人场景
多智能体强化学习因智能体间非平稳性与耦合性而极具挑战。马尔可夫博弈是刻画多智能体交互的常用框架。其中一类特殊类型——马尔可夫潜在博弈，可将多智能体博弈简化为单目标最优控制问题，目标函数为潜在函数。本文证明：广泛存在于工程中的多智能体协作覆盖问题可被建模为马尔可夫潜在博弈，并通过求解等价的单目标最优控制问题，学习参数化的闭环纳什均衡。实验表明，该算法在训练阶段较博弈论基线快10倍，策略执行时收敛更快。
原文摘要 · Abstract (English)
Multi-agent reinforcement learning is a challenging and active field of research due to the inherent nonstationary property and coupling between agents. A popular approach to modeling the multi-agent interactions underlying the multi-agent RL problem is the Markov Game. There is a special type of Markov Game, termed Markov Potential Game, which allows us to reduce the Markov Game to a single-objective optimal control problem where the objective function is a potential function. In this work, we prove that a multi-agent collaborative field coverage problem, which is found in many engineering applications, can be formulated as a Markov Potential Game, and we can learn a parameterized closed-loop Nash Equilibrium by solving an equivalent single-objective optimal control problem. As a result, our algorithm is 10x faster during training compared to a game-theoretic baseline and converges faster during policy execution.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。