Combining online and offline knowledge in UCT
Proceedings of the 24th international conference on Machine learning
A general solution to the graph history interaction problem
AAAI'04 Proceedings of the 19th national conference on Artifical intelligence
Achieving master level play in 9×9 computer go
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 3
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
IJCAI'09 Proceedings of the 21st international jont conference on Artifical intelligence
Efficient selectivity and backup operators in Monte-Carlo tree search
CG'06 Proceedings of the 5th international conference on Computers and games
Bandit based monte-carlo planning
ECML'06 Proceedings of the 17th European conference on Machine Learning
| Hi-index | 0.00 |
In this paper we present a framework for testing various algorithms that deal with transpositions in Monte-Carlo Tree Search (MCTS). We call this framework Upper Confidence bound for Direct acyclic graphs (UCD) as it constitutes an extension of Upper Confidence bound for Trees (UCT) for Direct acyclic graphs (DAG). When using transpositions in MCTS, a DAG is progressively developed instead of a tree. There are multiple ways to handle the exploration exploitation dilemma when dealing with transpositions. We propose parameterized ways to compute the mean of the child, the playouts of the parent and the playouts of the child. We test the resulting algorithms on several games. For all games, original configurations of our algorithms improve on state of the art algorithms.