Bootstrapping Monte Carlo Tree Search with an Imperfect Heuristic.
Truong-Huy Dinh NguyenWee Sun LeeTze-Yun LeongPublished in: ECML/PKDD (2) (2012)
Keyphrases
- monte carlo tree search
- tree search algorithm
- monte carlo
- game tree
- evaluation function
- bayesian reinforcement learning
- monte carlo search
- search algorithm
- temporal difference
- optimal solution
- vehicle routing problem
- alpha beta search
- temporal difference learning
- tree search
- game playing
- branch and bound
- learning experience
- linear programming
- dynamic programming