A Markov Decision Process (MDP) is a natural framework for formulating sequential decision-making problems under uncertainty. In recent years, researchers have greatly advanced algorithms for learning and acting in MDPs. This book reviews such algorithms, beginning with well-known dynamic programming methods for solving MDPs such as policy iteration and value iteration, then describes approximate dynamic programming methods such as trajectory based value iteration, and finally moves to reinforcement learning methods such as Q-Learning, SARSA, and least-squares policy iteration. It describes algorithms in a unified framework, giving pseudocode together with memory and iteration complexity analysis for each. Empirical evaluations of these techniques, with four representations across four domains, provide insight into how these algorithms perform with various feature sets in terms of running time and performance. This tutorial provides practical guidance for researchers seeking to extend DP and RL techniques to larger domains through linear value function approximation. The practical algorithms and empirical successes outlined also form a guide for practitioners trying to weigh computational costs, accuracy requirements, and representational concerns. Decision making in large domains will always be challenging, but with the tools presented here this challenge is not insurmountable.
Nicholas Roy is Associate Professor of Aeronautics and Astronautics at MIT and General Chair of RSS 2012.
„Über diesen Titel“ kann sich auf eine andere Ausgabe dieses Titels beziehen.
EUR 5,92 für den Versand von Vereinigtes Königreich nach Deutschland
Versandziele, Kosten & DauerAnbieter: Ria Christie Collections, Uxbridge, Vereinigtes Königreich
Zustand: New. In. Artikel-Nr. ria9781601987600_new
Anzahl: Mehr als 20 verfügbar
Anbieter: moluna, Greven, Deutschland
Zustand: New. Inhaltsverzeichnis1: Introduction 2: Dynamic Programming and Reinforcement Learning 3: Representations 4: Empirical Results 5: Summary. Acknowledgements. References.KlappentextA Markov Decision Process (. Artikel-Nr. 4231663
Anzahl: Mehr als 20 verfügbar
Anbieter: Revaluation Books, Exeter, Vereinigtes Königreich
Paperback. Zustand: Brand New. 92 pages. 8.98x5.98x0.16 inches. In Stock. Artikel-Nr. x-1601987609
Anzahl: 2 verfügbar