Robust approachability and regret minimization in games with partial monitoring

Details Robust approachability and regret minimization in games with partial monitoring Robust approachability and regret minimization in games with partial monitoring

2011-05-25

arxiv.org/abs/1105.4995v3

Mathematics

Statistics Theory

Scientific paper

Approachability has become a standard tool in analyzing earning algorithms in the adversarial online learning setup. We develop a variant of approachability for games where there is ambiguity in the obtained reward that belongs to a set, rather than being a single vector. Using this variant we tackle the problem of approachability in games with partial monitoring and develop simple and efficient algorithms (i.e., with constant per-step complexity) for this setup. We finally consider external regret and internal regret in repeated games with partial monitoring and derive regret-minimizing strategies based on approachability theory.

Affiliated with

Also associated with

No associations

Rating

Robust approachability and regret minimization in games with partial monitoring 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 Robust approachability and regret minimization in games with partial monitoring, we encourage you to share that experience with our LandOfFree.com community. Your opinion is very important and Robust approachability and regret minimization in games with partial monitoring will most certainly appreciate the feedback.

Rate now

Comments { 0 }

Profile ID: LFWR-SCP-O-191298