Consistency and cautious fictitious play
From MaRDI portal
Publication:673692
DOI10.1016/0165-1889(94)00819-4zbMATH Open0900.90423OpenAlexW2168281471MaRDI QIDQ673692FDOQ673692
Authors: Drew Fudenberg, David K. Levine 
Publication date: 28 February 1997
Published in: Journal of Economic Dynamics and Control (Search for Journal in Brave)
Full work available at URL: http://nrs.harvard.edu/urn-3:HUL.InstRepos:3198694
Recommendations
Cites Work
- The Well-Calibrated Bayesian
- Learning mixed equilibria
- Merging of Opinions with Increasing Information
- Belief affirming in learning processes
- Calibrated learning and correlated equilibrium
- Fictitious play, Shapley polygons, and the replicator equations
- Title not available (Why is that?)
- Three problems in learning mixed-strategy Nash equilibria
- The Evolution of Conventions
- The statistical mechanics of strategic interaction
- Cooperation and Effective Computability
- Steady State Learning and Nash Equilibrium
- Self-Calibrating Priors Do Not Exist
Cited In (68)
- Title not available (Why is that?)
- Nested replicator dynamics, nested logit choice, and similarity-based learning
- Convergence of strategies in simple co-adapting games
- Robustness properties in fictitious-play-type algorithms
- Independent learning in stochastic games
- Title not available (Why is that?)
- Dynamic benchmark targeting
- No-regret algorithms in on-line learning, games and convex optimization
- Simple uncoupled no-regret learning dynamics for extensive-form correlated equilibrium
- Learning in Games
- Payoff performance of fictitious play
- Note on universal conditional consistency
- Coordination between a sophisticated and fictitious player
- Replicator dynamics: old and new
- Heterogeneous beliefs and local information in stochastic fictitious play
- Mixed equilibria and dynamical systems arising from fictitious play in perturbed games
- AWESOME: a general multiagent learning algorithm that converges in self-play and learns a best response against stationary opponents
- Equilibria in large games with continuous procedures.
- A general class of adaptive strategies
- Time averages, recurrence and transience in the stochastic replicator dynamics
- Consistency of vanishingly smooth fictitious play
- Fictitious play in 3\(\times \)3 games: The transition between periodic and chaotic behaviour
- Exponential weight algorithm in continuous time
- Learning in games with strategic complementarities revisited
- Optimization incentive and relative riskiness in experimental stag-hunt games
- Belief-based equilibrium
- Sampled fictitious play is Hannan consistent
- Learning in network contexts: experimental results from simulations
- Learning about learning in games through experimental control of strategic interdependence
- Belief affirming in learning processes
- Information-theoretic bounded rationality and \(\epsilon\)-optimality
- Securing infrastructure facilities: when does proactive defense help?
- Learning in games with cumulative prospect theoretic preferences
- Learning and transfer in signaling games
- Learning, hypothesis testing, and Nash equilibrium.
- Learning purified mixed equilibria
- A two armed bandit type problem
- Learning in games using the imprecise Dirichlet model
- On attitude polarization under Bayesian learning with non-additive beliefs
- Evaluating generalizability and parameter consistency in learning models
- Learning to play games in extensive form by valuation
- Equilibrium and reinforcement learning in private-information games: An experimental study
- Stable games and their dynamics
- Reciprocity and cooperation in repeated coordination games: The principled-player approach
- Adaptive game playing using multiplicative weights
- Perspectives on multiagent learning
- Fast convergence in evolutionary models: a Lyapunov approach
- Conditional universal consistency.
- Minimizing regret: The general case
- Regret in the on-line decision problem
- Equilibrium play and adaptive learning in a three-person centipede game.
- An easier way to calibrate.
- Combining expert advice in reactive environments
- Multi-agent reinforcement learning: a selective overview of theories and algorithms
- Recency, consistent learning, and Nash equilibrium
- Regret minimization in repeated matrix games with variable stage duration
- Perturbations of set-valued dynamical systems, with applications to game theory
- Regret matching with finite memory
- On the rate of convergence of fictitious play
- Economists' models of learning
- A general criterion and an algorithmic framework for learning in multi-agent systems
- On the rate of convergence of fictitious play
- If multi-agent learning is the answer, what is the question?
- Dynamics in network interaction games
- A continuous-time approach to online optimization
- Optimal guessing: choice in complex environments
- Computing Bayes-Nash Equilibria in Combinatorial Auctions with Verification
- Learning and equilibrium transitions: stochastic stability in discounted stochastic fictitious play
This page was built for publication: Consistency and cautious fictitious play
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q673692)
