Evolving Agents for the Hanabi 2018 CIG Competition

By Rodrigo Canaan, Haotian Shen, Ruben Rodriguez Torrado, Julian Togelius, Andy Nealen, Stefan Menzel. 2018

26 citations recorded by the source corpus.

Hanabi is a cooperative card game with hidden information that has won important awards in the industry and received some recent academic attention. A two-track competition of agents for the game will take place in the 2018 CIG conference. In this paper, we develop a genetic algorithm that builds rule-based agents by determining the best sequence of rules from a fixed rule set to use as strategy. In three separate experiments, we remove human assumptions regarding the ordering of rules, add new, more expressive rules to the rule set and independently evolve agents specialized at specific game sizes. As result, we achieve scores superior to previously published research for the mirror and mixed evaluation of agents.

How researchers see this paper

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

Citations in the corpus

The Hanabi Challenge: A New Frontier for AI Research (2019, background): “When communicating with natural language, humans exploit theory of mind through their use of pragmatics : conveying meaning based on not only what was literally said, but also what is implicated ( i.e. , suggested) by the speaker based on the context [77 .”
Diverse Agents for Ad-Hoc Cooperation in Hanabi (2019, methodology): “Our 2018 competition entry, which took second place, is described in [17].”
Re-determinizing Information Set Monte Carlo Tree Search in Hanabi (2019, methodology): “[28] find helpful in their evolutionary search.”