An extension of a hierarchical reinforcement learning algorithm for multiagent settings

Autor:	Lambrou, Ioannis, Vassiliades, Vassilis, Christodoulou, Chris C.
Přispěvatelé:	Christodoulou, Chris C. [0000-0001-9398-5256]
Rok vydání:	2012
Předmět:	Reinforcement learning Hill climbing Multiagent Reinforcement Learning Taxi Domain Learning algorithms Hierarchical Reinforcement Learning Single-agent Hierarchical decompositions Problem domain Multi-agent reinforcement learning Taxicabs Multi agent systems Multi-agent setting
Zdroj:	9th European Workshop on Reinforcement Learning, EWRL 2011 Lect. Notes Comput. Sci.
Popis:	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. 7188 LNAI 261 272 Sponsors: Artificial Intelligence Australian National University NICTA PASCAL2 Conference code: 89968
Databáze:	OpenAIRE
Externí odkaz:	https://explore.openaire.eu/search/publication?articleId=od______4485::f483ee938c4b1564d8c98f737d0c410e http://gnosis.library.ucy.ac.cy/handle/7/54355 Zobrazit plný text záznamu