2024-03-29T14:28:20Zhttp://digital.csic.es/dspace-oai/requestoai:digital.csic.es:10261/29842020-01-17T07:57:16Zcom_10261_60com_10261_4col_10261_313
A Multi-Agent Architecture Integrating Learning and Fuzzy Techniques for Landmark-Based Robot Navigation
Busquets, Didac
López de Mántaras, Ramón
Sierra, Carles
Dietterich, Thomas G.
Fulbright Commission
Comisión Interministerial de Ciencia y Tecnología, CICYT (España)
Generalitat de Catalunya
Artificial intelligence
Machine Learning
Robotics
Multiagent Systems
Fuzzy Logic
La publicación original está disponible en www.springerlink.com.
This paper extends a navigation system implemented as a multi-agent system (MAS). The arbitration mechanism controlling the interactions between the agents was based on manually-tuned bidding functions. A difficulty with hand-tuning is that it is hard to handle situations involving complex tradeoffs. In this paper we explore the suitability of reinforcement learning for automatically tuning agents within a MAS to optimize a complex tradeoff, namely the camera use.
Fullbright Joint Research Project and Plan Nacional Project DPI 2000-1352-C02-02.
Dídac Busquets holds the CIRIT doctoral scholarship 2000FI-00191.
Peer reviewed
2008-02-19T11:44:28Z
2008-02-19T11:44:28Z
2002
comunicación de congreso
http://purl.org/coar/resource_type/c_5794
Topics in Artificial Intelligence, 5th Catalonian Conference on AI, CCIA 2002 Castellón, Spain, October 2002. Proceedings. Lecture Notes in Artificial Intelligence Vol. 2504, p.p.: 269-281, Springer-Verlag, 2002.
0302-9743
http://hdl.handle.net/10261/2984
http://dx.doi.org/10.13039/501100002809
http://dx.doi.org/10.13039/501100007273
en
open
240583 bytes
application/pdf
Springer