Hanabi is a cooperative game that challenges exist-ing AI techniques due to its focus on modeling the mental states ofother players to interpret and predict their behavior. While thereare agents that can achieve near-perfect scores in the game byagreeing on some shared strategy, comparatively little progresshas been made in ad-hoc cooperation settings, where partnersand strategies are not known in advance. In this paper, we showthat agents trained through self-play using the popular RainbowDQN architecture fail to cooperate well with simple rule-basedagents that were not seen during training and, conversely, whenthese agents are trained to play with any individual rule-basedagent, or even a mix of these agents, they fail to achieve goodself-play scores.
@article{arxiv.2004.13291,
title = {Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners},
author = {Rodrigo Canaan and Xianbo Gao and Youjin Chung and Julian Togelius and Andy Nealen and Stefan Menzel},
journal= {arXiv preprint arXiv:2004.13291},
year = {2020}
}