Feature discovery for problem solving systems
Feature discovery for problem solving systems
Temporal difference learning and TD-Gammon
Communications of the ACM
Neural-Symbolic Learning System: Foundations and Applications
Neural-Symbolic Learning System: Foundations and Applications
Behind Deep Blue: Building the Computer that Defeated the World Chess Champion
Behind Deep Blue: Building the Computer that Defeated the World Chess Champion
Automatic heuristic construction in a complete general game player
AAAI'06 proceedings of the 21st national conference on Artificial intelligence - Volume 2
Heuristic evaluation functions for general game playing
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Fluxplayer: a successful general game player
AAAI'07 Proceedings of the 22nd national conference on Artificial intelligence - Volume 2
Simulation-based approach to general game playing
AAAI'08 Proceedings of the 23rd national conference on Artificial intelligence - Volume 1
General game playing in AI research and education
KI'11 Proceedings of the 34th Annual German conference on Advances in artificial intelligence
Hi-index | 0.00 |
Unlike traditional game playing, General Game Playing is concerned with agents capable of playing classes of games. Given the rules of an unknown game, the agent is supposed to play well without human intervention. For this purpose, agent systems that use deterministic game tree search need to automatically construct a state value function to guide search. Successful systems of this type use evaluation functions derived solely from the game rules, thus neglecting further improvements by experience. In addition, these functions are fixed in their form and do not necessarily capture the game's real state value function. In this work we present an approach for obtaining evaluation functions on the basis of neural networks that overcomes the aforementioned problems. A network initialization extracted from the game rules ensures reasonable behavior without the need for prior training. Later training, however, can lead to significant improvements in evaluation quality, as our results indicate.