%Aigaion2 BibTeX export from Idiap Publications %Thursday 21 November 2024 11:47:19 AM @TECHREPORT{dimitrakakis:rr05-29, author = {Dimitrakakis, Christos and Bengio, Samy}, projects = {Idiap}, title = {Gradient estimates of return}, type = {Idiap-RR}, 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.}, pdf = {https://publications.idiap.ch/attachments/reports/2005/dimitrakakis-idiap-rr-05-29.pdf}, postscript = {ftp://ftp.idiap.ch/pub/reports/2005/dimitrakakis-idiap-rr-05-29.ps.gz}, ipdmembership={learning}, }