Multiple Tree for Partially Observable Monte-Carlo Tree Search
By David Auger. 2011
28 citations recorded by the source corpus.
We propose an algorithm for computing approximate Nash equilibria of partially observable games using Monte-Carlo tree search based on recent bandit methods. We obtain experimental results for the game of phantom tic-tac-toe, showing that strong strategies can be efficiently computed by our algorithm.
Subfields: Reinforcement Learning
How researchers see this paper
The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.
In Reinforcement Learning
- Karl Tuyls
- Julien Pérolat
- Marc Lanctot
- Yuxi Li
- Jean-Baptiste Lespiau
- David Silver
- Shayegan Omidshafiei
- Dustin Morrill
Citations in the corpus
- OpenSpiel: A Framework for Reinforcement Learning in Games (2019, background): “Game Reference(s) Status Backgammon Wikipedia Breakthrough Wikipedia Bridge bidding Wikipedia Catch [45] and [53, Appendix A] Coin Game [58] ∼ Connect Four Wikipedia Cooperative Box-Pushing [64] ∼ Chess Wikipedia First-price Sealed-bid Auction Wikipedia Go Wikipedia Goofspiel Wikipedia Havannah Wiki”
- Smooth UCT Search in Computer Poker (2015, result): “We first extend the work of [Auger, 2011] and [Cowling et al., 2012] to a general MCTS algorithm for extensive-form games, and then introduce Smooth UCT as a particular instantiation of this family of methods.”
- Self-play Monte-Carlo tree search in computer poker (2014, background): “(Auger 2011) and (Cowling, Powley, and Whitehouse 2012) study MCTS in imperfect information games and use the bandit method EXP3 (Auer et al.”
- A Survey of Monte Carlo Tree Search Methods (2012, background): “Progressive History was shown to perform well for some multi-player board games (7.3), indicating that it may be useful for multi-player games in general.”