Game State and Action Abstracting Monte Carlo Tree Search for General Strategy Game-Playing.
Alexander DockhornJorge Hurtado GruesoDominik JeurissenLinjie XuDiego Perez LiebanaPublished in: CoG (2021)
Keyphrases
- game playing
- monte carlo tree search
- game tree
- temporal difference learning
- video games
- monte carlo
- game tree search
- imperfect information
- multi player
- game play
- opponent modeling
- general game playing
- tic tac toe
- online game
- optimal strategy
- attitudes toward
- game players
- state space
- search algorithm
- human players
- board game
- evaluation function
- design process
- lower bound
- alpha beta search