Navigating the Landscape of Multiplayer Games

Abstract

Multiplayer games have long been used as testbeds in artificial intelligence research, aptly referred to as the Drosophila of artificial intelligence. Traditionally, researchers have focused on using well-known games to build strong agents. This progress, however, can be better informed by characterizing games and their topological landscape. Tackling this latter question can facilitate understanding of agents and help determine what game an agent should target next as part of its training. Here, we show how network measures applied to response graphs of large-scale games enable the creation of a landscape of games, quantifying relationships between games of varying sizes and characteristics. We illustrate our findings in domains ranging from canonical games to complex empirical games capturing the performance of trained agents pitted against one another. Our results culminate in a demonstration leveraging this information to generate new and interesting games, including mixtures of empirical games synthesized from real world games.

References in corpus (16)

• The Arcade Learning Environment: An Evaluation Platform for General Agents
• Dota 2 with Large Scale Deep Reinforcement Learning
• Stochastic Dynamics of Invasion and Fixation
• Clustering and Community Detection in Directed Networks: A Survey
• Cooperating with Machines
• A Unified Game-Theoretic Approach to Multiagent Reinforcement Learning
• Stochasticity and evolutionary stability
• OpenSpiel: A Framework for Reinforcement Learning in Games
• Multi-Agent Common Knowledge Reinforcement Learning
• Spectral properties of the Google matrix of the World Wide Web and other directed networks
• Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions
• Navigating the Topology of 2x2 Games: An Introductory Note on Payoff Families, Normalization, and Natural Order
• Escaping Prisoner's Dilemmas: From Discord to Harmony in the Landscape of 2x2 Games
• Finite-population evolution with rare mutations in asymmetric games
• A Generalized Training Approach for Multiagent Learning
• Multiagent Evaluation under Incomplete Information

Cited by in corpus (3)

• Signalling boosts the evolution of cooperation in repeated group interactions
• The graph structure of two-player games
• Visualising Multiplayer Game Spaces