Learning Position Evaluation Functions Used in Monte Carlo Softmax Search.
Harukazu IgarashiYuichi MoriokaKazumasa YamamotoPublished in: CoRR (2019)
Keyphrases
- monte carlo
- evaluation function
- temporal difference learning
- game tree
- game tree search
- minimax search
- reinforcement learning
- temporal difference
- td learning
- search algorithm
- markov chain
- monte carlo tree search
- alpha beta
- iterative deepening
- learning algorithm
- branching factor
- learning process
- monte carlo simulation
- heuristic function
- optimal strategy
- learning tasks
- search space
- machine learning
- function approximation
- search methods
- fixed point
- point processes
- particle filter
- monte carlo search