Computer Science
Home

Computer Science Colloquium

Im Rahmen des Informatik-Kolloquiums, das von den Instituten des Fachbereichs Informatik, der Österreichischen Gesellschaft für Informatik (ÖGI), der Arbeitsgemeinschaft für Datenverarbeitung (ADV) sowie der Österreichischen Computergesellschaft (OCG) abgehalten wird, spricht

Steffen Grünewälder

Technische Universität Berlin

über das Thema:

Convergence Results in Reinforcement Learning

Zeit: 2006-04-06 17:15:00.0, 60 Minuten
Ort: HS 13

Zusammenfassung

The term reinforcement learning refers to a category of machine learning techniques which deal with the estimation and maximization (through acting) of an abstract value named reward. The concept of reward driven learning is very general and hence it is possible to apply the techniques to a wide variety of problems: e.g. control systems for robots; adaptive websites, users provide feedback in terms of reward (very nice - very bad page) and an agent must learn to maximize this reward through generating the optimal website. This talk will be about the reward estimation problem with a focus on convergence speed analyzes of different methods. I will start with a short survey of basic concepts and terminology. After that I will discuss known convergence results and present new ones for two major techniques (temporal difference learning and monte carlo estimation).
Einladender: Prof. Dr. Sepp Hochreiter
Liste aller Vorträge
Last modified on Thursday, 01-Jan-1970 01:00:00 CET