Our conclusions are twofold: (1) in Bao, PrOM search performs better than OM search and sometimes also better than Minimax search even when no perfect information of the opponent is available, and (2) for an adequate performance of PrOM search, emphasis on the own evaluation function in the opponent model should be higher than assumed so far. In this paper we investigate two questions: (1) to which extent is PrOM search better than OM search and Minimax search in the game of Bao? and (2) which opponent type is most advantageous to use? To answer the second question we constructed Five evaluation functions which we applied in a tournament consisting of 352,000 games. We hypothesize that PrOM search is a better search mechanism than Opponent-Model search (OM search) and Minimax search. As of now, It has approximately 70 chance of winning each game, but I am trying to increase that number. The opponent is assumed to adopt at every move one of the opponent types ω i according to the probability Pr(ω i ). than OM search and Minimax search in the game of Bao and (2) which opponent type. If we got timeout in some place in MiniMax, then we return the last calculated direction. If we got to a specific depth, we calculate the heuristic value. If we got to children, we return \infty for a player win, -\infty for the rival win, and 0 for a tie. The game plays out every possible combination of moves from each position and. AI has had notable success in building high-performance game-playing. I'm using the MiniMax algorithm with a time limit to play the game. Lets take a look at Minimax, a tree search algorithm which. TicTacToe is a demonstration of the AI game playing minimax algorithm. In Probabilistic Opponent-Model search (PrOM search) the opponent is modelled by a mixed strategy of N opponent types ω 0. However we can generalize this approach to make it work with other board games such as Chess or Go.
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |