Survey of Self-Play in Reinforcement Learning

Abstract

In reinforcement learning (RL), the term self-play describes a kind of multi-agent learning (MAL) that deploys an algorithm against copies of itself to test compatibility in various stochastic environments. As is typical in MAL, the literature draws heavily from well-established concepts in classical game theory and so this survey quickly reviews some fundamental concepts. In what follows, we present a brief survey of self-play literature, its major themes, criteria, and techniques, and then conclude with an assessment of current shortfalls of the literature as well as suggestions for future directions.

arXiv comment8 pages

References in corpus (3)

• Online Bandit Learning against an Adaptive Adversary: from Regret to Policy Regret
• A Polynomial-time Nash Equilibrium Algorithm for Repeated Stochastic Games
• Foolproof Cooperative Learning