Scalable Evaluation of Multi-Agent Reinforcement Learning with Melting Pot

Joel Z. Leibo * 1 Edgar Duenez-Guzman * 1 Alexander Sasha Vezhnevets * 1 John P. Agapiou * 1 Peter Sunehag 1
       Raphael Koster 1 Jayd Matyas 1 Charles Beattie 1 Igor Mordatch 2 Thore Graepel 1

             Abstract                 eral recent calls to import the methodological stance con-
   Existing evaluation suites for multi-agent rein-       cerning the primacy of generalization from supervised learn-
   forc ...