← Search

Revan MacQueen

1 accepted papers

2023

Guarantees for Self-Play in Multiplayer Games via Polymatrix Decomposability

NeurIPS 2023poster

Self-play is a technique for machine learning in multi-agent systems where a learning algorithm learns by interacting with copies of itself. Self-play is useful for generating large quantities of data for learning, but has the drawback that the agents the learner will face post-training may have dra…