Regret minimization in repeated matrix games with variable stage duration
From MaRDI portal
Publication:926893
DOI10.1016/j.geb.2007.07.006zbMath1134.91330OpenAlexW2045249027MaRDI QIDQ926893
Publication date: 21 May 2008
Published in: Games and Economic Behavior (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1016/j.geb.2007.07.006
approachabilityregret minimizationHannan consistencybest-response envelopecalibrated playno-regret strategiesrepeated matrix gamesvariable duration games
Related Items (3)
Approachability, regret and calibration: implications and equivalences ⋮ Unnamed Item ⋮ Opportunistic Approachability and Generalized No-Regret Problems
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Consistency and cautious fictitious play
- An analog of the minimax theorem for vector payoffs
- Calibrated learning and correlated equilibrium
- A wide range no-regret theorem
- Regret in the on-line decision problem
- A proof of calibration via Blackwell's approachability theorem.
- Adaptive game playing using multiplicative weights
- Conditional universal consistency.
- An easier way to calibrate.
- Calibrated forecasting and merging
- Minimizing regret: The general case
- Online calibrated forecasts: memory efficiency versus universality for learning in games
- Zero-sum two-person semi-Markov games
- Asymptotic calibration
- A Simple Adaptive Procedure Leading to Correlated Equilibrium
- Learning Theory
- The Nonstochastic Multiarmed Bandit Problem
- Guaranteed performance regions in Markovian systems with competing decision makers
- Adaptive Heuristics
- Prediction, Learning, and Games
- Elements of Information Theory
- Calibration with Many Checking Rules
- The Empirical Bayes Envelope and Regret Minimization in Competitive Markov Decision Processes
- Stochastic Games
- A general class of adaptive strategies
This page was built for publication: Regret minimization in repeated matrix games with variable stage duration
