α-Rank: Multi-Agent Evaluation by Evolution
Scientific reports, pp. 99372019.
We introduce α-Rank, a principled evolutionary dynamics methodology, for the evaluation and ranking of agents in large-scale multi-agent interactions, grounded in a novel dynamical game-theoretic solution concept called Markov-Conley chains (MCCs). The approach leverages continuous-time and discrete-time evolutionary dynamical systems app...More
Full Text (Upload PDF)
PPT (Upload PPT)