Regret in the on-line decision problem
From MaRDI portal
Publication:1818283
DOI10.1006/game.1999.0740zbMath0984.91025OpenAlexW2135730283MaRDI QIDQ1818283
Rakesh V. Vohra, Dean P. Foster
Publication date: 2 May 2001
Published in: Games and Economic Behavior (Search for Journal in Brave)
Full work available at URL: http://www.dklevine.com/archive/refs4569.pdf
Related Items (50)
Achieving Unbounded Resolution inFinitePlayer Goore Games Using Stochastic Automata, and Its Applications ⋮ Approachability in population games ⋮ Replicator dynamics: old and new ⋮ A general internal regret-free strategy ⋮ Learning correlated equilibria in games with compact sets of strategies ⋮ Online calibrated forecasts: memory efficiency versus universality for learning in games ⋮ A general criterion and an algorithmic framework for learning in multi-agent systems ⋮ Rationality Authority for Provable Rational Behavior ⋮ Approachability with bounded memory ⋮ Robust mean field games ⋮ Dynamic benchmark targeting ⋮ Unnamed Item ⋮ Constrained no-regret learning ⋮ Prior‐free dynamic allocation under limited liability ⋮ Predicting a binary sequence almost as well as the optimal biased coin ⋮ No-regret algorithms in on-line learning, games and convex optimization ⋮ Learning to compete, coordinate, and cooperate in repeated games using reinforcement learning ⋮ Unnamed Item ⋮ Optimal Exploration–Exploitation in a Multi-armed Bandit Problem with Non-stationary Rewards ⋮ Learning, hypothesis testing, and Nash equilibrium. ⋮ Approachability, regret and calibration: implications and equivalences ⋮ Regret minimization in repeated matrix games with variable stage duration ⋮ Load balancing without regret in the bulletin board model ⋮ Randomized prediction of individual sequences ⋮ Deterministic calibration and Nash equilibrium ⋮ Repeated Games with Incomplete Information ⋮ Exponential weight algorithm in continuous time ⋮ Opinion dynamics and learning in social networks ⋮ A general class of adaptive strategies ⋮ Stable games and their dynamics ⋮ Computer science and decision theory ⋮ A Robust Saturated Strategy for $n$-Player Prisoner's Dilemma ⋮ Internal regret in on-line portfolio selection ⋮ Internal regret in on-line portfolio selection ⋮ Maximin effects in inhomogeneous large-scale data ⋮ Learning by trial and error ⋮ When autonomous agents model other agents: an appeal for altered judgment coupled with mouths, ears, and a little more tape ⋮ Strategic learning in games with symmetric information. ⋮ A wide range no-regret theorem ⋮ Price probabilities: a class of Bayesian and non-Bayesian prediction rules ⋮ Adaptive game playing using multiplicative weights ⋮ Conditional universal consistency. ⋮ Minimizing regret: The general case ⋮ Unnamed Item ⋮ If multi-agent learning is the answer, what is the question? ⋮ Agendas for multi-agent learning ⋮ The possible and the impossible in multi-agent learning ⋮ A hierarchy of prescriptive goals for multiagent learning ⋮ Online Discrete Optimization in Social Networks in the Presence of Knightian Uncertainty ⋮ Calibration and Internal No-Regret with Random Signals
Uses Software
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Consistency and cautious fictitious play
- An analog of the minimax theorem for vector payoffs
- On repeated games with incomplete information played by non-Bayesian players
- The weighted majority algorithm
- Calibrated learning and correlated equilibrium
- Conditional universal consistency.
- An easier way to calibrate.
- Prediction in the worst case
- Universal prediction of individual sequences
- Weak Approachability
- Asymptotic calibration
- A Randomization Rule for Selecting Forecasts
- Universal Portfolios
- Choice Without Beliefs
- A Simple Adaptive Procedure Leading to Correlated Equilibrium
- How to use expert advice
- On Pseudo-Games
This page was built for publication: Regret in the on-line decision problem
