Publication

Policy invariance under reward transformations for multi-objective reinforcement learning

Mannion, Patrick
; 
Devlin, Sam
; 
Mason, Karl
; 
Duggan, Jim
; 
Howley, Enda
Identifiers
http://hdl.handle.net/10379/12634
 https://doi.org/10.13025/28670
Publication Date
2017-11-01
Keywords
reinforcement learning, multi-objective, potential-based, reward shaping, multi-agent systems, decision-making
Type
Article
Downloads
Show all metadata
Citation
Mannion, Patrick; Devlin, Sam; Mason, Karl; Duggan, Jim; Howley, Enda (2017). Policy invariance under reward transformations for multi-objective reinforcement learning. Neurocomputing 263 , 60-73
Abstract
Funder
Publisher
Elsevier BV
Publisher DOI
Rights
Attribution-NonCommercial-NoDerivs 3.0 Ireland
cbn
Collections
Externally hosted open access publications with University of Galway authors (2)