Local Approximation of Difference Evaluation Functions.
Mitchell K. ColbyTheodore Duchow-PressleyJen Jen ChungKagan TumerPublished in: AAMAS (2016)
Keyphrases
- evaluation function
- temporal difference
- convex functions
- iterative deepening
- expected outcome
- two player games
- branching factor
- game tree search
- temporal difference learning
- alpha beta
- td learning
- heuristic function
- image segmentation
- learning experience
- evolutionary algorithm
- general game playing
- objective function
- monte carlo search