UCD: Upper Confidence Bound for Rooted Directed Acyclic Graphs

@article{Saffidine2010UCDUC,
  title={UCD: Upper Confidence Bound for Rooted Directed Acyclic Graphs},
  author={Abdallah Saffidine and Tristan Cazenave and Jean M{\'e}hat},
  journal={2010 International Conference on Technologies and Applications of Artificial Intelligence},
  year={2010},
  pages={467-473}
}
In this paper we present a framework for testing various algorithms that deal with transpositions in Monte-Carlo Tree Search (MCTS). When using transpositions in MCTS, a Directed Acyclic Graph (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… CONTINUE READING
Highly Cited
This paper has 23 citations. REVIEW CITATIONS
15 Citations
16 References
Similar Papers

Similar Papers

Loading similar papers…