Computer Science – Artificial Intelligence
Scientific paper
2006-04-05
Computer Science
Artificial Intelligence
10 pages, 2 figures; IDIAP Research Report
Scientific paper
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.
No associations
LandOfFree
Nearly optimal exploration-exploitation decision thresholds does not yet have a rating. At this time, there are no reviews or comments for this scientific paper.
If you have personal experience with Nearly optimal exploration-exploitation decision thresholds, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Nearly optimal exploration-exploitation decision thresholds will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-418471