logo Idiap Research Institute        
 [BibTeX] [Marc21]
Gradient estimates of return
Type of publication: Idiap-RR
Citation: dimitrakakis:rr05-29
Number: Idiap-RR-29-2005
Year: 2005
Institution: IDIAP
Note: Published in PASCAL Workshop in Principled Methods of Trading Exploration and Exploitation, London, UK, 2005
Abstract: The exploration-exploitation trade-off that arises when one considers simple point estimates of expected returns no longer appears when full distributions are considered. This work develops a simple gradient-based approach for mainting such distributions and investigates methods for using them to direct exploration.
Userfields: ipdmembership={learning},
Projects Idiap
Authors Dimitrakakis, Christos
Bengio, Samy
Crossref by dimitrakakis:pascal:2005
Added by: [UNK]
Total mark: 0
  • dimitrakakis-idiap-rr-05-29.pdf
  • dimitrakakis-idiap-rr-05-29.ps.gz