Self-play reinforcement learning has given rise to capable game-playing agents in a number of complex domains such as Go and Chess. These players were evaluated against other state-of-the-art agents and professional human players and have demonstrated competence surpassing these opponents. But does strong competition performance also mean the agents can (weakly or strongly) solve the game? Or even approximately solve the game? No existing work has considered this question. We propose aligning our evaluation of self-play agents with metrics of strong/weakly solving strategies to provide a measure of an agent’s strength. Using small games, we establish methodology on measuring the strength of a self-play agent and its gap between a strongly-solving agent, one which plays optimally regardless of an opponent’s decisions. We provide metrics that use ground-truth data from small, solved games to quantify the strength of an agent and its ability to generalize to a domain. We then perform an analysis of a self-play agent using scaled-down versions of Chinese checkers.
Feb 24th 2022
Feb 1st 2022
Read this research paper, co-authored by Amii Fellow and Canada CIFAR AI Chairs Neil Burch and Michael Bowling: Rethinking formal models of partially observable multiagent decision making
Dec 6th 2021
Read this research paper, co-authored by Amii Fellow and Canada CIFAR AI Chairs Neil Burch and Micheal Bowling: Player of Games
Looking to build AI capacity? Need a speaker at your event?
Get involved in Alberta's growing AI ecosystem! Speaker, sponsorship, and letter of support requests welcome.
Curious about study options under one of our researchers? Want more information on training opportunities?