TL;DR本研究提出三种完全分散的自然 Actor Critic (MAN)算法,具有全局收敛性和在交通网络中降低平均拥堵率的实际应用。
Abstract
multi-agent actor-critic algorithms are an important part of the
reinforcement learning paradigm. We propose three fully decentralized
multi-agent natural actor-critic (MAN) algorithms in this work. The objective