Proceedings of the IEEE · 2004 · 128 citations · 12 references
ComputingComputer ScienceAlgorithmsArtificial IntelligenceMachine LearningArtificial Intelligence StrategyEvolutionary ComputationEvolutionary OptimizationGame PlayingGenetic AlgorithmsPopulation-based SearchComputer ChessGame-playing AgentsLearning In Games
A central challenge of artificial intelligence is to create machines that can learn from their own experience and perform at the level of human experts. Using an evolutionary algorithm, a computer program has learned to play chess by playing games against itself. The program learned to evaluate chessboard configurations by using the positions of pieces, material and positional values, and neural networks to assess specific sections of the chessboard. During evolution, the program improved its play by almost 400 rating points. Testing under simulated tournament conditions against Pocket Fritz 2.0 indicated that the evolved program performs above the master level.
12
Evolutionary computation: Toward a new philosophy of machine intelligence
Thomas B�ck · Complexity · 1997 · 1.5K citations
Practical issues in temporal difference learning
Gerald Tesauro · Machine Learning · 1992 · 800 citations · Full text