logo Idiap Research Institute        
 [BibTeX] [Marc21]
Nearly optimal exploration-exploitation decision thresholds
Type of publication: Idiap-RR
Citation: dimitrakakis:rr06-12
Number: Idiap-RR-12-2006
Year: 2006
Institution: IDIAP
Note: To appear in ICANN 2006
Abstract: While in general trading off exploration and exploitation in reinforcement learning is hard, under some formulations relatively simple solutions exist. Optimal decision thresholds for the multi-armed bandit problem, one for the infinite horizon discounted reward case and one for the finite horizon undiscounted reward case are derived, which make the link between the reward horizon, uncertainty and the need for exploration explicit. From this result follow two practical approximate algorithms, which are illustrated experimentally.
Userfields: ipdmembership={learning},
Keywords:
Projects Idiap
Authors Dimitrakakis, Christos
Crossref by dimitrakakis:icann:2006
Added by: [UNK]
Total mark: 0
Attachments
  • dimitrakakis-idiap-rr-06-12.pdf
  • dimitrakakis-idiap-rr-06-12.ps.gz
Notes