Toward a Classification of Finite Partial-Monitoring Games

Details Toward a Classification of Finite Partial-Monitoring Games Toward a Classification of Finite Partial-Monitoring Games

2011-02-10

arxiv.org/abs/1102.2041v3

Computer Science

Computer Science and Game Theory

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.

Affiliated with

Also associated with

No associations

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

Comments { 0 }

Profile ID: LFWR-SCP-O-694195