In the empirical approach to game-theoretic analysis (EGTA), the model of the game comes
not from declarative representation, but is derived by interrogation of a procedural …

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 …

The Nash equilibrium—a combination of choices by the players of a game from which no
self-interested player would deviate—is the predominant solution concept in game theory …

This paper investigates a population-based training regime based on game-theoretic
principles called Policy-Spaced Response Oracles (PSRO). PSRO is general in the sense …

Similar to the role of Markov decision processes in reinforcement learning, Markov games
(also called stochastic games) lay down the foundation for the study of multi-agent …

Two-player, constant-sum games are well studied in the literature, but there has been limited
progress outside of this setting. We propose Joint Policy-Space Response Oracles (JPSRO) …

In many coordination problems, independently reasoning humans are able to discover
mutually compatible policies. In contrast, independently trained self-play policies are often …

We consider the age-old problem of allocating items among different agents in a way that is
efficient and fair. Two papers, by Dolev et al. and Ghodsi et al., have recently studied this …

Promoting behavioural diversity is of critical importance in multi-agent reinforcement
learning, since it helps the agent population maintain robust performance when …

Self-play, characterized by agents' interactions with copies or past versions of itself, has
recently gained prominence in reinforcement learning. This paper first clarifies the …