Evaluating and Modelling Hanabi Playing Agents

The hanabi engine was described in the Evaluating and Modelling Hanabi-playing agents paper in CEC 2017.

author={J. Walton-Rivers and P. R. Williams and R. Bartle and D. Perez-Liebana and S. M. Lucas},
booktitle={2017 IEEE Congress on Evolutionary Computation (CEC)},
title={Evaluating and modelling Hanabi-playing agents},
keywords={Monte Carlo methods;computer games;knowledge based systems;multi-agent systems;search problems;trees (mathematics);Hanabi-playing agent evaluation;Hanabi-playing agent modelling;IS-MCTS;collaborative card game;game-playing strength;hidden- information;information set-Monte Carlo tree search agent;predictor capabilities;rule-based agents;Artificial intelligence;Cognition;Computational modeling;Games;Monte Carlo methods;Planning;Standards},

Entrant's Papers

These are papers written by competition entrants.

Evolving Agents for the Hanabi 2018 CIG Competition

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.

  title={Evolving Agents for the Hanabi 2018 CIG Competition},
  author={Canaan, Rodrigo and Shen, Haotian and Torrado, Ruben and Togelius, Julian and Nealen, Andy and Menzel, Stefan},
  booktitle={2018 IEEE Conference on Computational Intelligence and Games (CIG)},

If you have written a paper using the framework, contact me and I'll add it to the list

Source Code

Source code for agents that have permitted it are available on that agent's Comet page.

The framework, website and competition software are all Free Software (GPLv3), and can be found on our gitlab server