Re-determinizing Information Set Monte Carlo Tree Search in Hanabi
By James Goodman. 2019
14 citations recorded by the source corpus.
This technical report documents the winner of the Computational Intelligence in Games(CIG) 2018 Hanabi competition. We introduce Re-determinizing IS-MCTS, a novel extension of Information Set Monte Carlo Tree Search (IS-MCTS) that prevents a leakage of hidden information into opponent models that can occur in IS-MCTS, and is particularly severe in Hanabi. Re-determinizing IS-MCTS scores higher in Hanabi for 2-4 players than previously published work at the time of the competition. Given the 40ms competition time limit per move we use a learned evaluation function to estimate leaf node values and avoid full simulations during MCTS. For the Mixed track competition, in which the identity of the other players is unknown, a simple Bayesian opponent model is used that is updated as each game proceeds.
Subfields: Artificial Intelligence, Computer Vision and Pattern Recognition
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
- Jakob N. Foerster
- Sergey Levine
- Yoshua Bengio
- Pieter Abbeel
- Hengyuan Hu
- Yuxi Li
- Marc G. Bellemare
- Ruslan Salakhutdinov
In Computer Vision and Pattern Recognition
- Luc Van Gool
- Abhinav Kumar Gupta
- Dacheng Tao
- Jitendra Malik
- Trevor Darrell
- Ming-Hsuan Yang
- Xiaogang Wang
- Andrea Vedaldi
Citations in the corpus
- Simplified Action Decoder for Deep Multi-Agent Reinforcement Learning (2019, methodology): “Examples of using search in Hanabi include Goodman (2019).”
- The Hanabi Challenge: A New Frontier for AI Research (2019, methodology): “ace agent, \Monte Carlo NN", achieved a score of 20.57. According to the website these scores are averaged across the results for two to ve players. The winning agent, developed by James Goodman [54], won both the Mirror and Mixed tracks; it used Information Set Monte Carlo Tree Search [55] as ”
- Diverse Agents for Ad-Hoc Cooperation in Hanabi (2019, methodology): “The winner of the competition was a variant of Monte Carlo Tree Search [14] by Goodman [15] designed to deal with problems of strategy fusion and nonlocality that arise from executing tree search in a hidden information environment.”