dc.contributor.author | Lambrou, Ioannis | en |
dc.contributor.author | Vassiliades, Vassilis | en |
dc.contributor.author | Christodoulou, Chris C. | en |
dc.creator | Lambrou, Ioannis | en |
dc.creator | Vassiliades, Vassilis | en |
dc.creator | Christodoulou, Chris C. | en |
dc.date.accessioned | 2019-11-13T10:40:54Z | |
dc.date.available | 2019-11-13T10:40:54Z | |
dc.date.issued | 2012 | |
dc.identifier.issn | 0302-9743 | |
dc.identifier.uri | http://gnosis.library.ucy.ac.cy/handle/7/54355 | |
dc.description.abstract | This paper compares and investigates single-agent reinforcement learning (RL) algorithms on the simple and an extended taxi problem domain, and multiagent RL algorithms on a multiagent extension of the simple taxi problem domain we created. In particular, we extend the Policy Hill Climbing (PHC) and the Win or Learn Fast-PHC (WoLF-PHC) algorithms by combining them with the MAXQ hierarchical decomposition and investigate their efficiency. The results are very promising for the multiagent domain as they indicate that these two newly-created algorithms are the most efficient ones from the algorithms we compared. © 2012 Springer-Verlag. | en |
dc.source | 9th European Workshop on Reinforcement Learning, EWRL 2011 | en |
dc.source.uri | https://www.scopus.com/inward/record.uri?eid=2-s2.0-84861673287&doi=10.1007%2f978-3-642-29946-9_26&partnerID=40&md5=2bb84cac41a9e8db20f54622e5007393 | |
dc.subject | Multi agent systems | en |
dc.subject | Learning algorithms | en |
dc.subject | Hierarchical decompositions | en |
dc.subject | Reinforcement learning | en |
dc.subject | Problem domain | en |
dc.subject | Multi-agent setting | en |
dc.subject | Hierarchical Reinforcement Learning | en |
dc.subject | Hill climbing | en |
dc.subject | Multi-agent reinforcement learning | en |
dc.subject | Multiagent Reinforcement Learning | en |
dc.subject | Single-agent | en |
dc.subject | Taxi Domain | en |
dc.subject | Taxicabs | en |
dc.title | An extension of a hierarchical reinforcement learning algorithm for multiagent settings | en |
dc.type | info:eu-repo/semantics/article | |
dc.identifier.doi | 10.1007/978-3-642-29946-9_26 | |
dc.description.volume | 7188 LNAI | en |
dc.description.startingpage | 261 | |
dc.description.endingpage | 272 | |
dc.author.faculty | 002 Σχολή Θετικών και Εφαρμοσμένων Επιστημών / Faculty of Pure and Applied Sciences | |
dc.author.department | Τμήμα Πληροφορικής / Department of Computer Science | |
dc.type.uhtype | Article | en |
dc.description.notes | <p>Sponsors: Artificial Intelligence | en |
dc.description.notes | Australian National University | en |
dc.description.notes | NICTA | en |
dc.description.notes | PASCAL2 | en |
dc.description.notes | Conference code: 89968</p> | en |
dc.source.abbreviation | Lect. Notes Comput. Sci. | en |
dc.contributor.orcid | Christodoulou, Chris C. [0000-0001-9398-5256] | |
dc.gnosis.orcid | 0000-0001-9398-5256 | |