Autonomous combinatorial search (AS) represents a new field in combinatorial problem solving. Its major standpoint and originality is that it considers that problem solvers must be able to perform self-improvement operations. It involves both short-term reactive reconfiguration and long-term improvement through self-analysis of the performance. In some AS implementations, the solver itself is used at a metalevel to do some reasoning about its performance. In general AS systems perform some analysis of a solver performance and change their inner configuration to more efficiently accommodate their external problem-solving duties. This is the first book dedicated to this topic, and it will act as a reference for researchers, engineers and postgraduates in the areas of constraint programming, machine learning, evolutionary computing, and feedback control theory. After the editors' introduction to autonomous search, the chapters are focused on tuning algorithm parameters, autonomous complete (tree-based) constraint solvers, control in metaheuristics, and heuristics. . The contributors are among the leading researchers in the areas of heuristics, optimization, evolutionary computing and constraints. The book will be ofbenefit to researchers, engineers and postgraduates in the areas of constraint programming, machine learning and evolutionary computing. This is the first book dedicated to this topic. INDICE: An Introduction to Autonomous Search.-Part I – Offline Configuration.-Evolutionary Algorithm Parameters and Methods to Tune Them. Automated Algorithm Configuration and Parameter Tuning. Case-Based Reasoning for Autonomous Constraint Solving. Learning a Mixture of Search Heuristics. Part II – Online Control. An Investigation of Reinforcement Learning for Reactive Search Optimization. Adaptive Operator Selection and Management in Evolutionary Algorithms.Parameter Adaptation in Ant Colony Optimization. Part III – New Directions and Applications. Continuous Search in Constraint Programming. Control-Based Clause Sharing in Parallel SAT Solving. Learning Feature-Based Heuristic Functions.
- ISBN: 978-3-642-21433-2
- Editorial: Springer Berlin Heidelberg
- Encuadernacion: Cartoné
- Páginas: 308
- Fecha Publicación: 30/06/2011
- Nº Volúmenes: 1
- Idioma: Inglés