On imitating Connect-4 game trajectories using an approximate n-tuple evaluation function.
Thomas Philip RunarssonSimon M. LucasPublished in: CIG (2015)
Keyphrases
- evaluation function
- two player games
- monte carlo tree search
- minimax search
- alpha beta pruning
- computer chess
- game tree search
- monte carlo search
- game tree
- human players
- temporal difference
- general game playing
- table tennis
- alpha beta
- branching factor
- temporal difference learning
- iterative deepening
- moving objects
- nash equilibrium
- monte carlo
- state action
- heuristic function
- computer games
- optimality criterion
- perfect information
- td learning
- game playing
- expected outcome
- policy evaluation
- opponent modeling
- game design
- game play
- educational games