Sciweavers

Share
CORR
2006
Springer

Nearly optimal exploration-exploitation decision thresholds

11 years 1 months ago
Nearly optimal exploration-exploitation decision thresholds
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.
Christos Dimitrakakis
Added 11 Dec 2010
Updated 15 Dec 2011
Type Journal
Year 2006
Where CORR
Authors Christos Dimitrakakis
Comments (0)
books