Adaptive game playing using multiplicative weights
From MaRDI portal
Publication:1818286
DOI10.1006/GAME.1999.0738zbMATH Open0964.91007OpenAlexW2106887613MaRDI QIDQ1818286FDOQ1818286
Authors: Yoav Freund, Robert E. Schapire 
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
Recommendations
Cites Work
- Title not available (Why is that?)
- Title not available (Why is that?)
- Present Position and Potential Developments: Some Personal Views: Statistical Theory: The Prequential Approach
- Probability Inequalities for Sums of Bounded Random Variables
- The weighted majority algorithm
- Title not available (Why is that?)
- Title not available (Why is that?)
- Title not available (Why is that?)
- Consistency and cautious fictitious play
- An analog of the minimax theorem for vector payoffs
- A sublinear-time randomized approximation algorithm for matrix games
- Asymptotic calibration
- Universal Portfolios
- How to use expert advice
- Fast probabilistic algorithms for Hamiltonian circuits and matchings
- Regret in the on-line decision problem
- Universal portfolios with side information
- Title not available (Why is that?)
- Title not available (Why is that?)
- On‐Line Portfolio Selection Using Multiplicative Updates
- A game of prediction with expert advice
- Universal prediction of individual sequences
- Coding theorems for individual sequences
- Fast Approximation Algorithms for Fractional Packing and Covering Problems
- Prediction in the worst case
- Title not available (Why is that?)
- A Randomization Rule for Selecting Forecasts
- Universal sequential coding of single messages
Cited In (64)
- Note on universal conditional consistency
- Boosting the margin: a new explanation for the effectiveness of voting methods
- Replicator dynamics: old and new
- A multiplicative weights update algorithm for packing and covering semi-infinite linear programs
- Gambling, computational information and encryption security
- AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
- On learning algorithms for Nash equilibria
- A general class of adaptive strategies
- On incremental approximate saddle-point computation in zero-sum matrix games
- Exponential weight algorithm in continuous time
- Potential-based algorithms in on-line prediction and game theory
- Belief-based equilibrium
- No regrets about no-regret
- A stochastic variant of replicator dynamics in zero-sum games and its invariant measures
- Linear programming with online learning
- Bayesian adversarial multi-node bandit for optimal smart grid protection against cyber attacks
- Load balancing without regret in the bulletin board model
- A multiplicative weights update algorithm for MINLP
- Deterministic calibration and Nash equilibrium
- Constrained no-regret learning
- Effective short-term opponent exploitation in simplified poker
- Committee polyhedral separability: complexity and polynomial approximation
- Online learning of Nash equilibria in congestion games
- Learning in games via reinforcement and regularization
- Network inspection for detecting strategic attacks
- Perspectives on multiagent learning
- Generalized mirror descents in congestion games
- An adjusted payoff-based procedure for normal form games
- Fictitious play in networks
- Equilibrium routing under uncertainty
- On the stability of an adaptive learning dynamics in traffic games
- Dynamic benchmark targeting
- Adaptive Play in Multiplayer Bargaining Situations
- A payoff-based learning procedure and its application to traffic games
- Regret bounds for sleeping experts and bandits
- Near-optimal no-regret algorithms for zero-sum games
- Multi-armed bandits based on a variant of simulated annealing
- Game problem of adaptive selection of versions and an algorithm for solving it
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- The multiplicative weights update method: a meta-algorithm and applications
- Regret minimization in repeated matrix games with variable stage duration
- Near-linear algorithms for geometric hitting sets and set covers
- Opinion dynamics with limited information
- A multiplicative weight updates algorithm for packing and covering semi-infinite linear programs
- Zero-sum polymatrix games: a generalization of minmax
- Solving zero-sum games using best-response oracles with applications to search games
- Proportional response dynamics in the Fisher market
- Competitive On-line Statistics
- Title not available (Why is that?)
- Tatonnement beyond gross substitutes? Gradient descent to the rescue
- Efficient learning equilibrium
- On the Number of Iterations for Dantzig--Wolfe Optimization and Packing-Covering Approximation Algorithms
- Multicommodity network flows: A survey. II: Solution methods
- A natural adaptive process for collective decision-making
- Randomized strategies for robust combinatorial optimization with approximate separation
- Multiagent learning for competitive opinion optimization
- The vanishing learning rate asymptotic for linear \(L^2\)-boosting
- Independent learning in stochastic games
- Solving maxmin optimization problems via population games
- Opinion dynamics with limited information
- No-regret algorithms in on-line learning, games and convex optimization
- Infinitesimal gradient boosting
- Memory loss can prevent chaos in games dynamics
- Adversarial bandits with knapsacks
This page was built for publication: Adaptive game playing using multiplicative weights
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1818286)
