Sampled fictitious play for approximate dynamic programming

DOI10.1016/j.cor.2011.01.023zbMath1215.90048OpenAlexW2085697350MaRDI QIDQ547121

Robert L. Smith, Archis Ghate, Marina A. Epelman

Publication date: 30 June 2011

Published in: Computers \& Operations Research (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.cor.2011.01.023

zbMATH Keywords

stochastic dynamic optimizationcomputational game theorysimulation optimization

Mathematics Subject Classification ID

Stochastic programming (90C15) Applications of game theory (91A80) Dynamic programming (90C39) Rationality and learning in game theory (91A26)

Related Items

Parameter-free sampled fictitious play for solving deterministic dynamic programming problems

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Simulation-based algorithms for Markov decision processes.
• A survey of some simulation-based algorithms for Markov decision processes
• A genetic algorithm for the multidimensional knapsack problem
• The boundedness of all products of a pair of matrices is undecidable
• \({\mathcal Q}\)-learning
• Fictitious play property for games with identical interests
• An iterative method of solving a game
• 10.1162/153244303768966102
• A Decentralized Approach to Discrete Optimization via Simulation: Application to Network Flow
• A Game-Theoretic Approach to Efficient Power Management in Sensor Networks
• Scheduling manufacturing systems with work-in-process inventory control: multiple-part-type systems
• Payoff-Based Dynamics for Multiplayer Weakly Acyclic Games
• The Evolution of Conventions
• Approximate Dynamic Programming
• An Adaptive Sampling Algorithm for Solving Markov Decision Processes
• A Fictitious Play Approach to Large-Scale Optimization
• Finite-time analysis of the multiarmed bandit problem