# Diverse Agents for Ad-Hoc Cooperation in Hanabi

## TL;DR

This paper explores using Quality Diversity algorithms to generate diverse agent populations for ad-hoc cooperation in Hanabi, aiming to improve modeling of unknown players and adaptive agent development.

## Contribution

It introduces a novel approach using Quality Diversity algorithms to generate diverse Hanabi agents for ad-hoc cooperation evaluation.

## Key findings

- Proposed a new agent generator based on Quality Diversity algorithms.
- Discussed metrics for comparing agent generators.
- Highlighted potential for building adaptive Hanabi agents.

## Abstract

In complex scenarios where a model of other actors is necessary to predict and interpret their actions, it is often desirable that the model works well with a wide variety of previously unknown actors. Hanabi is a card game that brings the problem of modeling other players to the forefront, but there is no agreement on how to best generate a pool of agents to use as partners in ad-hoc cooperation evaluation. This paper proposes Quality Diversity algorithms as a promising class of algorithms to generate populations for this purpose and shows an initial implementation of an agent generator based on this idea. We also discuss what metrics can be used to compare such generators, and how the proposed generator could be leveraged to help build adaptive agents for the game.