Diverse Agents for Ad-Hoc Cooperation in Hanabi

By Rodrigo Canaan, Julian Togelius, Andy Nealen, Stefan Menzel. 2019

50 citations recorded by the source corpus.

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.

Subfields: Artificial Intelligence

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Artificial Intelligence

Citations in the corpus

Learned Belief Search: Efficiently Improving Policies in Partially Observable Settings (2021, background): “There has been recent work on ad-hoc team play and zero-shot coordination, in which agents are paired with unknown partners (Canaan et al., 2019; Walton-Rivers et al., 2017; Hu et al., 2020).”
Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning (2019, background): “Recently there have also been attempts to train agents that are robust to different team-mates (Canaan et al., 2019) and even to extend to human-AI collaboration (Liang et al., 2019).”
Improving Policies via Search in Cooperative Partially Observable Games (2019, background): “Lastly, there is recent work on ad-hoc team play in Han-abi, in which agents get evaluated against a pool of different teammates (Canaan et al. 2019; Walton-Rivers et al. 2017).”