Adaptive-predictive Game-playing Programs
University of California, Santa Cruz, Computer Research Laboratory, 1990 - Machine learning - 28 pages
Abstract: "Adaptive-predictive search (APS) is a new method by which systems can improve their search performance through experience. It is believed that the development of such methods is critical as currently a tremendous amount of computational results are potentially wasted by not integrating search and partial search results into the knowledge of a problem-solving system. In the adaptive-predictive search model pattern formation and associative recall are used to improve or replace search. In this paper the theory, background and motivations behind the model are presented and its application to two-player game-playing programs is discussed.
What people are saying - Write a review
We haven't found any reviews in the usual places.
1-ply search adaptive pattern adaptive-predictive search model apply Artificial Intelligence assignment problem associative recall Chess Computer chess positions chess program chunk Colin 89 Computer converges credit assignment database of patterns develop domain-specific knowledge domains edge estimated evaluation function example flip found by chaining genetic algorithms goal graph guide search heuristic heuristic search Hexapawn immediate predecessors improve search knowledge base Korf 88 Learning System Levinson 85 Machine Learning mechanism methods minimax more-general-than move nodes number of patterns occur partial ordering pattern formation pattern representation language Pattern Representation Scheme pattern-weight pairs Patterns are represented Patterns P4 pawn piece differential player pre-move primitive patterns problem query replace search representational change retrieval algorithm rithms Santa Cruz search knowledge search tree Section sequence specific patterns squares stored subgoals subgraph supervised learning Sutton 81 system finds temporal difference learning temporal-difference learning terns Tic-Tac-Toe triples triplets variance weight updating wp wp