{alpha}-Rank: Multi-Agent Evaluation by Evolution

arXiv: Artificial Intelligence, 2019.

Cited by: 0|Views296

Abstract:

We introduce {alpha}-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- and discrete-time evolutionary dynamical systems ap...More

Code:

Data:

Your rating :
0

 

Tags
Comments