# Evaluating the Rainbow DQN Agent in Hanabi with Unseen Partners

arXiv: https://arxiv.org/abs/2004.13291 · HTML: https://mlsanity.com/paper/2004.13291/

## Key facts

- Cited by 2 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 28 Apr 2020.

## Built on by (most cited first, 2 of 2)

- [Deep Interactive Bayesian Reinforcement Learning via Meta-Learning](https://mlsanity.com/paper/2101.03864/) (2021)
- [Generalized Beliefs for Cooperative AI](https://mlsanity.com/paper/2206.12765/) (2022)

## Abstract (arXiv)

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.