Calibrated learning and correlated equilibrium

DOI10.1006/game.1997.0595zbMath0894.90188OpenAlexW2073242866MaRDI QIDQ1378013

Publication date: 4 March 1998

Published in: Games and Economic Behavior (Search for Journal in Brave)

Full work available at URL: https://repository.upenn.edu/cgi/viewcontent.cgi?article=1008&context=statistics_papers

zbMATH Keywords

learning rule correlated equilibria sequence of plays

Mathematics Subject Classification ID

Multistage and repeated games (91A20)

Related Items

A general internal regret-free strategy, Belief-based equilibrium, An experiment on learning with limited information: nonconvergence, experimentation cascades, and the advantage of being slow., Learning correlated equilibria in games with compact sets of strategies, Computing equilibria: a computational complexity perspective, AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents, Online calibrated forecasts: memory efficiency versus universality for learning in games, Introduction to the special issue on learning and computational game theory, Inverse Game Theory: Learning Utilities in Succinct Games, Strong robustness to incomplete information and the uniqueness of a correlated equilibrium, Belief affirming in learning processes, The query complexity of correlated equilibria, Approachability of convex sets in generalized quitting games, Stochastic uncoupled dynamics and Nash equilibrium, Regret matching with finite memory, Rationality and bounded rationality, Mixing time and stationary expected social welfare of logit dynamics, Constrained no-regret learning, On adaptive heuristics that converge to correlated equilibrium, Selecting efficient correlated equilibria through distributed learning, Approachability with delayed information, Opinion dynamics with limited information, Dynamics in network interaction games, No-regret algorithms in on-line learning, games and convex optimization, Correlated beliefs: predicting outcomes in \(2\times 2\) games, Learning in games with cumulative prospect theoretic preferences, On the Geometry of Nash and Correlated Equilibria with Cumulative Prospect Theoretic Preferences, Approachability of convex sets in games with partial monitoring, Learning, hypothesis testing, and Nash equilibrium., Approachability, regret and calibration: implications and equivalences, On the communication complexity of approximate Nash equilibria, Regret minimization in repeated matrix games with variable stage duration, Load balancing without regret in the bulletin board model, Strong approachability, Deterministic calibration and Nash equilibrium, Correlated Equilibria and Communication in Games, Learning in Games, Learning to play efficient coarse correlated equilibria, Consistency and cautious fictitious play, Unnamed Item, LEARNING TO FACE STOCHASTIC DEMAND, Smooth calibration, leaky forecasts, finite recall, and Nash dynamics, The importance of memory for price discovery in decentralized markets, Local smoothness and the price of anarchy in splittable congestion games, Bounding the inefficiency of outcomes in generalized second price auctions, Opinion dynamics and learning in social networks, How long to equilibrium? The communication complexity of uncoupled equilibrium procedures, Controlling the losing probability in a monotone game, Learning in network contexts: experimental results from simulations, A general class of adaptive strategies, Playing monotone games to understand learning behaviors, Opinion dynamics with limited information, Computer science and decision theory, A differential game on Wasserstein space. Application to weak approachability with partial monitoring, The myth of the folk theorem, A payoff-based learning procedure and its application to traffic games, Special issue: Learning in games: a symposium in honor of David Blackwell., Regret in the on-line decision problem, Conditional universal consistency., Calibrated forecasting and merging, Multi-agent learning for engineers, 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, On the stability of an adaptive learning dynamics in traffic games, Partial Monitoring—Classification, Regret Bounds, and Algorithms, Opportunistic Approachability and Generalized No-Regret Problems, On the empirical relevance of correlated equilibrium, Exponential weight approachability, applications to calibration and regret minimization, Correlated equilibria in homogeneous good Bertrand competition, Equilibrium routing under uncertainty, Calibration and Bayesian learning., Payoff performance of fictitious play

Cites Work