Computer Science – Learning
Scientific paper
2011-06-13
Computer Science
Learning
Presented at the NIPS 2011 conference
Scientific paper
We consider an adversarial online learning setting where a decision maker can choose an action in every stage of the game. In addition to observing the reward of the chosen action, the decision maker gets side observations on the reward he would have obtained had he chosen some of the other actions. The observation structure is encoded as a graph, where node i is linked to node j if sampling i provides information on the reward of j. This setting naturally interpolates between the well-known "experts" setting, where the decision maker can view all rewards, and the multi-armed bandits setting, where the decision maker can only view the reward of the chosen action. We develop practical algorithms with provable regret guarantees, which depend on non-trivial graph-theoretic properties of the information feedback structure. We also provide partially-matching lower bounds.
Mannor Shie
Shamir Ohad
No associations
LandOfFree
From Bandits to Experts: On the Value of Side-Observations 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 From Bandits to Experts: On the Value of Side-Observations, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and From Bandits to Experts: On the Value of Side-Observations will most certainly appreciate the feedback.
Profile ID: LFWR-SCP-O-429482