Mean Field for Markov Decision Processes: From Discrete to Continuous Optimization

DOI10.1109/TAC.2012.2186176MaRDI QIDQ5352941zbMATH OpenFDO

Authors Nicolas Gast, Bruno Gaujal, Jean-Yves Le Boudec

Publication date 8 September 2017

Published in IEEE Transactions on Automatic Control (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1109/TAC.2012.2186176

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Cited in

(26)

• The complexity of synchronizing Markov decision processes
• Distributed control of multi-agent systems with random parameters and a major agent
• A mean field absorbing control model for interacting objects systems
• A mean field approach for discounted zero-sum games in a class of systems of interacting objects
• Approximation and mean field control of systems of large populations
• Game-theoretic frameworks for epidemic spreading and human decision-making: a review
• A mean field capital accumulation game with HARA utility
• A limit theorem for Markov decision processes
• Mean field Markov decision processes
• Mean field stochastic games with discrete states and mixed players
• Nonlinear Markov processes in big networks
• Discrete-time control for systems of interacting objects with unknown random disturbance distributions: a mean field approach
• An overview for Markov decision processes in queues and networks
• Control to flocking of the kinetic Cucker-Smale model
• Nonlinear diffusions and stable-like processes with coefficients depending on the median or var
• The mean-field computation in a supermarket model with server multiple vacations
• Control systems of interacting objects modeled as a game against nature under a mean field approach
• Extremal shift rule for continuous-time zero-sum Markov games
• Mean-field-game model of corruption
• Stochastic Mitra-Wan forestry models analyzed as a mean field optimal control problem
• On the control of density-dependent stochastic population processes with time-varying behavior
• Model-free mean-field reinforcement learning: mean-field MDP and mean-field Q-learning
• A mean field approach for optimization in discrete time
• Continuous-time mean field Markov decision models
• Recent developments in machine learning methods for stochastic control and games
• Large population discounted zero-sum games with unknown disturbance distribution: a mean-field approach

This page was built for publication: Mean Field for Markov Decision Processes: From Discrete to Continuous Optimization

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q5352941)