CBR for state value function approximation in reinforcement learning

Autor(en): Gabel, T
Riedmiller, M
Herausgeber: MunozAvila, H
Ricci, F
Stichwörter: Computer Science; Computer Science, Artificial Intelligence
Erscheinungsdatum: 2005
Herausgeber: SPRINGER-VERLAG BERLIN
Journal: CASE-BASED REASONING RESEARCH AND DEVELOPMENT, PROCEEDINGS
Lecture Notes in Artificial Intelligence
Volumen: 3620
Startseite: 206
Seitenende: 221
Zusammenfassung: 
CBR is one of the techniques that can be applied to the task of approximating a function over high-dimensional, continuous spaces. In Reinforcement Learning systems a learning agent is faced with the problem of assessing the desirability of the state it finds itself in. If the state space is very large and/or continuous the availability of a suitable mechanism to approximate a value function - which estimates the value of single states - is of crucial importance. In this paper, we investigate the use of case-based methods to realise that task. The approach we take is evaluated in a case study in robotic soccer simulation.
Beschreibung: 
6th International Conference on Case-Based Reasoning, Chicago, IL, AUG 23-26, 2005
ISBN: 9783540281740
ISSN: 03029743

Show full item record

Google ScholarTM

Check

Altmetric