Toward a Classification of Finite Partial-Monitoring Games

Computer Science – Computer Science and Game Theory

Scientific paper

Rate now

  [ 0.00 ] – not rated yet Voters 0   Comments 0

Details

Submitted for review to Theoretical Computer Science (Special Issue of the conference Algorithmic Learning Theory 2010)

Scientific paper

Partial-monitoring games constitute a mathematical framework for sequential decision making problems with imperfect feedback: The learner repeatedly chooses an action, opponent responds with an outcome, and then the learner suffers a loss and receives a feedback signal, both of which are fixed functions of the action and the outcome. The goal of the learner is to minimize his total cumulative loss. We make progress towards the classification of these games based on their minimax expected regret. Namely, we classify almost all games with two outcomes and finite number of actions: We show that their minimax expected regret is either zero, $\widetilde{\Theta}(\sqrt{T})$, $\Theta(T^{2/3})$, or $\Theta(T)$ and we give a simple and efficiently computable classification of these four classes of games. Our hope is that the result can serve as a stepping stone toward classifying all finite partial-monitoring games.

No associations

LandOfFree

Say what you really think

Search LandOfFree.com for scientists and scientific papers. Rate them and share your experience with other people.

Rating

Toward a Classification of Finite Partial-Monitoring Games 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 Toward a Classification of Finite Partial-Monitoring Games, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Toward a Classification of Finite Partial-Monitoring Games will most certainly appreciate the feedback.

Rate now

     

Profile ID: LFWR-SCP-O-694195

  Search
All data on this website is collected from public sources. Our data reflects the most accurate information available at the time of publication.