Multi-agent case-based reasoning for cooperative reinforcement learners

Autor(en): Gabel, Thomas
Riedmiller, Martin
Herausgeber: RothBerghofer, TR
Goker, MH
Guvenir, HA
Stichwörter: Computer Science; Computer Science, Artificial Intelligence
Erscheinungsdatum: 2006
Herausgeber: SPRINGER-VERLAG BERLIN
Journal: ADVANCES IN CASE-BASED REASONING, PROCEEDINGS
Lecture Notes in Artificial Intelligence
Volumen: 4106
Startseite: 32
Seitenende: 46
Zusammenfassung: 
In both research fields, Case-Based Reasoning and Reinforcement Learning, the system under consideration gains its expertise from experience. Utilizing this fundamental common ground as well as further characteristics and results of these two disciplines, in this paper we develop an approach that facilitates the distributed learning of behaviour policies in cooperative multi-agent domains without communication between the learning agents. We evaluate our algorithms in a case study in reactive production scheduling.
Beschreibung: 
8th European Conference on Case-Based Reasoning, Fethiye, TURKEY, SEP 04-07, 2006
ISBN: 9783540368434
ISSN: 03029743

Show full item record

Google ScholarTM

Check

Altmetric