Monte-Carlo Tree Reductions for Stochastic Games
Jouandeau, Nicolas; Cazenave, Tristan (2014), Monte-Carlo Tree Reductions for Stochastic Games, in Cheng, Shin-Ming; Day, Min-Yuh, Technologies and Applications of Artificial Intelligence, Springer, p. 228-238. 10.1007/978-3-319-13987-6_22
TypeCommunication / Conférence
External document linkhttps://hal.archives-ouvertes.fr/hal-02317159
Conference title19th International Conference, TAAI 2014
Book titleTechnologies and Applications of Artificial Intelligence
Book authorCheng, Shin-Ming; Day, Min-Yuh
Number of pages396
MetadataShow full item record
Laboratoire d'analyse et modélisation de systèmes pour l'aide à la décision [LAMSADE]
Abstract (EN)Monte-Carlo Tree Search (MCTS) is a powerful paradigm for perfect information games. When considering stochastic games, the tree model that represents the game has to take chance and a huge branching factor into account. As effectiveness of MCTS may decrease in such a setting, tree reductions may be useful. Chance-nodes are a way to deal with random events. Move-groups are another way to deal efficiently with a large branching factor by regrouping nodes. Group-nodes are regrouping only reveal moves and enable a choice between reveal moves and classical moves. We present various policies to use such reductions for the stochastic game Chinese Dark Chess. Move-groups, chance-nodes and group-nodes are compared.
Subjects / KeywordsPerfect Information; Stochastic Game; Main Loop; Classical Move; Select Function
Showing items related by title and author.