Constrained no-regret learning

DOI10.1016/J.JMATECO.2020.02.002MaRDI QIDQ2178579zbMATHOpenAlexFDO

Authors Ye Du, Ehud Lehrer

Publication date 11 May 2020

Published in Journal of Mathematical Economics (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.jmateco.2020.02.002

zbMATH Keywords

approachabilityon-line learning algorithmno-regret strategyconstrained no-regret

Mathematics Subject Classification ID

Decision theory (91B06)

Recommendations

• Online Learning with Constraints
• Online learning with sample path constraints
• Learning algorithms for finite horizon constrained Markov decision processes
• Trading regret for efficiency: online convex optimization with long term constraints
• Regret Minimization Under Partial Monitoring

Cites work

• scientific article; zbMATH DE number 3128728 (Why is no real title available?)
• scientific article; zbMATH DE number 1233801 (Why is no real title available?)
• A Simple Adaptive Procedure Leading to Correlated Equilibrium
• A general class of adaptive strategies
• Adaptive game playing using multiplicative weights
• An analog of the minimax theorem for vector payoffs
• Approachability in infinite dimensional spaces
• Approachability with bounded memory
• Approachability with delayed information
• Approachability, regret and calibration: implications and equivalences
• Bandits with switching costs, \(T^{2/3}\) regret
• Calibrated learning and correlated equilibrium
• Conditional universal consistency.
• Excludability and Bounded Computational Capacity
• Internal regret in on-line portfolio selection
• Learning, regret minimization, and equilibria
• Online learning with sample path constraints
• Prediction, Learning, and Games
• Regret Minimization Under Partial Monitoring
• Regret in the on-line decision problem
• Robust option pricing: Hannan and Blackwell meet Black and Scholes
• The multiplicative weights update method: a meta-algorithm and applications

Cited in

(4)

• Online Learning with Constraints
• Approachability with constraints
• Memory-Constrained No-Regret Learning in Adversarial Multi-Armed Bandits
• Online learning with sample path constraints

This page was built for publication: Constrained no-regret learning

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2178579)