Temporal-difference search in computer Go.
David SilverRichard S. SuttonMartin MüllerPublished in: Mach. Learn. (2012)
Keyphrases
- temporal difference
- temporal difference learning
- monte carlo
- evaluation function
- monte carlo tree search
- game tree search
- function approximation
- td learning
- reinforcement learning
- model free
- search algorithm
- action selection
- step size
- linear combination
- search space
- dynamic programming
- policy iteration
- function approximators
- cost function
- data sets