An extension of a hierarchical reinforcement learning algorithm for multiagent settings
Ημερομηνία
2012ISSN
0302-9743Source
9th European Workshop on Reinforcement Learning, EWRL 2011Volume
7188 LNAIPages
261-272Google Scholar check
Keyword(s):
Metadata
Εμφάνιση πλήρους εγγραφήςΕπιτομή
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.
Collections
Cite as
Related items
Showing items related by title, author, creator and subject.
-
Article
Spiking neural networks with different reinforcement learning (RL) schemes in a multiagent setting
Christodoulou, Chris C.; Cleanthous, A. (2010)This paper investigates the effectiveness of spiking agents when trained with reinforcement learning (RL) in a challenging multiagent task. In particular, it explores learning through rewardmodulated spike-timing dependent ...
-
Conference Object
Charging Policies for PHEVs used for Service Delivery: A Reinforcement Learning Approach
Panayiotou, Tania; Chatzis, Sotirios P.; Panayiotou, Christos; Ellinas, Georgios (2018)This work examines a cost optimization problem for plug-in hybrid electric vehicles (PHEVs) used for service delivery, in the presence of energy consumption uncertainty. For the cost optimization problem, an optimal policy ...
-
Article
Multiagent reinforcement learning: Spiking and nonspiking agents in the Iterated Prisoner's Dilemma
Vassiliades, Vassilis; Cleanthous, A.; Christodoulou, Chris C. (2011)This paper investigates multiagent reinforcement learning (MARL) in a general-sum game where the payoffs' structure is such that the agents are required to exploit each other in a way that benefits all agents. The contradictory ...