Set-valued approachability and online learning with partial monitoring

MaRDI QIDQ2934107zbMATH OpenFDO

Authors Shie Mannor, Vianney Perchet, Gilles Stoltz

Publication date 8 December 2014

Full work available at URL http://jmlr.csail.mit.edu/papers/v15/mannor14a.html

zbMATH Keywords

approachabilitylearningpartial monitoringregret

Mathematics Subject Classification ID

Learning and adaptive systems in artificial intelligence (68T05) Rationality and learning in game theory (91A26)

Recommendations

• On a unified framework for approachability with full or partial monitoring
• A primal condition for approachability with partial monitoring
• Approachability of convex sets in games with partial monitoring
• Partial monitoring -- classification, regret bounds, and algorithms
• Response-based approachability with applications to generalized no-regret problems

Cited in

(9)

• Approachability of convex sets in generalized quitting games
• Approachability with constraints
• On a unified framework for approachability with full or partial monitoring
• A primal condition for approachability with partial monitoring
• Opportunistic approachability and generalized no-regret problems
• Approachability of convex sets in games with partial monitoring
• Best-of-both-worlds algorithms for partial monitoring
• Pseudonorm approachability and applications to regret minimization
• Cleaning up the neighborhood: a full classification for adversarial partial monitoring

This page was built for publication: Set-valued approachability and online learning with partial monitoring

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2934107)