Deakin University
Browse

Balanced Q-learning: Combining the influence of optimistic and pessimistic targets

Version 2 2024-06-03, 01:04
Version 1 2023-10-20, 03:32
journal contribution
posted on 2024-06-03, 01:04 authored by Thommen Karimpanal GeorgeThommen Karimpanal George, Hung LeHung Le, M Abdolshah, Santu RanaSantu Rana, Sunil GuptaSunil Gupta, Truyen TranTruyen Tran, Svetha VenkateshSvetha Venkatesh
Balanced Q-learning: Combining the influence of optimistic and pessimistic targets

History

Journal

Artificial Intelligence

Volume

325

Article number

104021

Pagination

104021-104021

Location

Amsterdam, The Netherlands

ISSN

0004-3702

Language

en

Publication classification

C1 Refereed article in a scholarly journal

Publisher

Elsevier BV