ABSTRACT
Opponent models are necessary in games where the game state is only partially known to the player, since the player must infer the state of the game based on the opponents actions. This paper presents an architecture and a process for developing neural network game players that utilize explicit opponent models in order to improve game play against unseen opponents. The model is constructed as a mixture over a set of cardinal opponents, i.e. opponents that represent maximally distinct game strategies. The model is trained to estimate the likelihood that the opponent will make the same move as each of the cardinal opponents would in a given game situation. Experiments were performed in the game of Guess It, a simple game of imperfect information that has no optimal strategy for defeating specific opponents. Opponent modeling is therefore crucial to play this game well. Both opponent modeling and game-playing neural networks were trained using NeuroEvolution of Augmenting Topologies (NEAT). The results demonstrate that game-playing provided with the model outperform networks not provided with the model when played against the same previously unseen opponents. The cardinal mixture architecture therefore constitutes a promising approach for general and dynamic opponent modeling in game-playing.
- Billings, D., Papp, D., Schaeffer, J., and Szafron, D. Opponent Modeling in Poker. Proceedings of 15th National Conference of the American Association on Artificial Intelligence. AAAI Press, Madison, WI, 1998, 493--498. Google ScholarDigital Library
- Davidson, A., Billings, D., Schaeffer, J., and Szafron, D. Improved Opponent Modeling in Poker. Proceedings of the 2000 International Conference on Artificial Intelligence (ICAI'2000). 1999, 1467--1473.Google Scholar
- Davidson, A. Using Artificial Neural Networks to Model Opponents in Texas Hold 'Em. Unpublished manuscript; http://spaz.ca/aaron/poker/nnpoker.pdf. 1999.Google Scholar
- DiPietro, A., Barone, L., and While L. Learning In RoboCup Keepaway Using Evolutionary Algorithms. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002). Kaufmann, San Francisco, 2002, 1065--1072. Google ScholarDigital Library
- Green, C. Phased Searching with NEAT: Alternating Between Complexification and Simplification. Unpublished manuscript; http://sharpneat.sourceforge.net/phasedsearch.html. 2004Google Scholar
- Gomez, F. and Miikkulainen, R. 2-D Pole Balancing with Recurrent Evolutionary Networks. Proceedings of the International Conference on Artificial Neural Networks (ICANN-98). Springer, Berlin, 1998, 425--430.Google ScholarCross Ref
- Isaacs, R. A card game with bluffing,. The American MathematicalMonthly, vol. 62. 1955, 99--108.Google ScholarCross Ref
- Kohonen, T. The Self-Organizing Map. Proceedings of the IEEE, vol. 78. 1990, 1464--1480.Google ScholarCross Ref
- Korb, K., Nicholson, A., and Jitnah, N. Bayesian Poker. Proceedings of the Conference on Uncertainty in Artificial Intelligence (UAI-99). 1999, 343--350. Google ScholarDigital Library
- Ponsen, M., Munoz-Avila, H., Spronck, P., and Aha, D. Automatically Generating Game Tactics via Evolutionary Learning. AI Magazine, 27(3). AAAI Press, Madison, WI, 2005, 75--84.Google Scholar
- Riley, P., and Veloso, A. Planning for Distributed Execution Through Use of Probabilistic Opponent Models. IJCAI-2001 Workshop PRO-2: Planning under Uncertainty and Incomplete Information. 2001.Google Scholar
- Southey, F., Bowling, M., Larson, B., Piccione, C., Burch, N., and Billings, D. Bayes' Bluff: Opponent Modeling in Poker. Proceedings of the 21st Conference on Uncertainty in Artificial Intelligence (UAI-05). 2005, 550--558.Google Scholar
- Spronck, P., Ponsen, M., Sprinkhuizen-Kuyper, I., and Postma, E. Adaptive Game AI with Dynamic Scripting. Machine Learning, 63. Kluwer, Hingham, MA, 2005, 217--248. Google ScholarDigital Library
- Stanley, K. and Miikkulainen, R. Continual Coevolution Through Complexification, Proceedings of the Genetic and Evolutionary Computation Conference (GECCO-2002). Kaufmann, San Francisco, 2002, 113--120. Google ScholarDigital Library
- Whiteson, S., Kohl, N., Miikkulainen, R., and Stone, P. Evolving RoboCup Keepaway Players through Task Decomposition. Proceedings of the Genetic and Evolutionary Computation Conference (GECCO 2003). Kaufmann, San Francisco, 2003, 356--368. Google ScholarDigital Library
Index Terms
- Evolving explicit opponent models in game playing
Recommendations
Real-time neuroevolution in the NERO video game
In most modern video games, character behavior is scripted; no matter how many times the player exploits a weakness, that weakness is never repaired. Yet, if game characters could learn through interacting with the player, behavior could improve as the ...
How AI can change the way we play games
CF '12: Proceedings of the 9th conference on Computing FrontiersWhile artificial intelligence (AI) in games is often associated with enhancing the behavior of non-player characters, at its cutting edge AI offers the potential for entirely new kinds of gaming experiences. In this talk I will focus on this frontier of ...
A Profitable Online No-Limit Poker Playing Agent
WI-IAT '14: Proceedings of the 2014 IEEE/WIC/ACM International Joint Conferences on Web Intelligence (WI) and Intelligent Agent Technologies (IAT) - Volume 03The No-Limit Texas Hold'em variant of Poker is the game that is most frequently used to assess new developments in incomplete information problems, through the development of game playing agents. For this particular game, current state-of-the-art ...
Comments