Response-based approachability with applications to generalized no-regret problems

MaRDI QIDQ5502129zbMATH OpenFDO

Authors Andrey Bernstein, Nahum Shimkin

Publication date 17 August 2015

Full work available at URL https://arxiv.org/abs/1312.7658, http://jmlr.csail.mit.edu/papers/v16/bernstein15a.html

zbMATH Keywords

no-regret algorithms

Mathematics Subject Classification ID

Dynamic programming (90C39) 2-person games (91A05) Multistage and repeated games (91A20)

Recommendations

• An online convex optimization approach to Blackwell's approachability
• Opportunistic approachability and generalized no-regret problems
• Approachability in Stackelberg stochastic games with vector costs
• Approachability, regret and calibration: implications and equivalences
• Approachability in repeated games: Computational aspects and a Stackelberg variant

Cited in

(11)

• Solving optimization problems with Blackwell approachability
• Pseudonorm approachability and applications to regret minimization
• Exponential weight approachability, applications to calibration and regret minimization
• Set-valued approachability and online learning with partial monitoring
• An online convex optimization approach to Blackwell's approachability
• scientific article; zbMATH DE number 7626715 (Why is no real title available?)
• An Approximate Dynamic Programming Approach to Repeated Games with Vector Losses
• Approachability in repeated games: Computational aspects and a Stackelberg variant
• Approachability, regret and calibration: implications and equivalences
• Approachability in Stackelberg stochastic games with vector costs
• Opportunistic approachability and generalized no-regret problems

This page was built for publication: Response-based approachability with applications to generalized no-regret problems

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5502129)