Papers - SanchoGGP/ggp-base GitHub Wiki
A collection of relevant papers.
MCTS selection policy
- Algorithms for the multi-armed bandit problem, Kuleshov & Precup, 2010?
- On Bayesian Upper Confidence Bounds for Bandit Problems, Kaufmann et al., 2012.
- [Monte-Carlo Tree Search Enhancements for Havannah] (https://dke.maastrichtuniversity.nl/m.winands/documents/StankiewiczACG2011.pdf)
- [N-Grams and the Last-Good-Reply Policy applied in General Game Playing] (http://www.ru.is/~yngvi/pdf/TakWB12.pdf).
Parallel MCTS
See Parallel MCTS for a review of these papers.
- Distributed Monte-Carlo Tree Search for Games with Team of Cooperative Agents, Filip, 2013.
- Scalable Distributed Monte-Carlo Tree Search, Yoshizoe et al., 2011.
- A Lock-free Multithreaded Monte-Carlo Tree Search Algorithm, Enzenberger & Muller, 2009
- Parallel Monte-Carlo Tree Search, Chaslot et al., 2008.
- On the Parallelization of UCT, Cazenave & Jouandeau, 2007.
Other MCTS
- A Principled Approach to the Problem of Chunking in UCT, Chee et al., 2015
- UCD: Upper confidence bound for rooted directed acyclic graphs, Saffidine et al., 2012.
GIGA Proceedings
The GIGA workshop is directly to related to General Game Playing and the proceedings typically contain useful papers. The later proceedings have been reviewed from a Sancho perspective.