Adaptive game playing using multiplicative weights

DOI10.1006/game.1999.0738zbMath0964.91007OpenAlexW2106887613MaRDI QIDQ1818286

Publication date: 1 February 2000

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

Full work available at URL: https://doi.org/10.1006/game.1999.0738

zbMATH Keywords

repeated game asymptotic optimality multiplicative weights algorithm

Mathematics Subject Classification ID

Noncooperative games (91A10) Multistage and repeated games (91A20)

Related Items

Replicator dynamics: old and new, On Learning Algorithms for Nash Equilibria, On incremental approximate saddle-point computation in zero-sum matrix games, Belief-based equilibrium, AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents, Generalized mirror descents in congestion games, Dynamic benchmark targeting, Network Inspection for Detecting Strategic Attacks, Competitive On-line Statistics, Constrained no-regret learning, On the Number of Iterations for Dantzig--Wolfe Optimization and Packing-Covering Approximation Algorithms, A multiplicative weight updates algorithm for packing and covering semi-infinite linear programs, Gambling, Computational Information and Encryption Security, Committee polyhedral separability: complexity and polynomial approximation, Opinion dynamics with limited information, A stochastic variant of replicator dynamics in zero-sum games and its invariant measures, No-regret algorithms in on-line learning, games and convex optimization, Infinitesimal gradient boosting, Randomized strategies for robust combinatorial optimization with approximate separation, Independent learning in stochastic games, A Multiplicative Weights Update Algorithm for Packing and Covering Semi-infinite Linear Programs, Fictitious play in networks, Tatonnement beyond gross substitutes? Gradient descent to the rescue, Solving Zero-Sum Games Using Best-Response Oracles with Applications to Search Games, Unnamed Item, Regret bounds for sleeping experts and bandits, Regret minimization in repeated matrix games with variable stage duration, Load balancing without regret in the bulletin board model, Deterministic calibration and Nash equilibrium, Linear programming with online learning, Exponential weight algorithm in continuous time, Note on universal conditional consistency, Proportional response dynamics in the Fisher market, A general class of adaptive strategies, Opinion dynamics with limited information, Bayesian adversarial multi-node bandit for optimal smart grid protection against cyber attacks, A payoff-based learning procedure and its application to traffic games, Near-optimal no-regret algorithms for zero-sum games, Near-linear algorithms for geometric hitting sets and set covers, Zero-Sum Polymatrix Games: A Generalization of Minmax, Multi-armed bandits based on a variant of simulated annealing, Effective short-term opponent exploitation in simplified poker, Boosting the margin: a new explanation for the effectiveness of voting methods, On randomized fictitious play for approximating saddle points over convex sets, Perspectives on multiagent learning, No regrets about no-regret, Learning in Games via Reinforcement and Regularization, An Adjusted Payoff-Based Procedure for Normal Form Games, On the stability of an adaptive learning dynamics in traffic games, Online Learning of Nash Equilibria in Congestion Games, Multi-agent reinforcement learning: a selective overview of theories and algorithms, Equilibrium routing under uncertainty, Efficient learning equilibrium

Cites Work