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

From MaRDI portal
Publication:5352941

DOI10.1109/TAC.2012.2186176zbMath1369.90186MaRDI QIDQ5352941

Nicolas Gast, Jean-Yves Le Boudec, Bruno Gaujal

Publication date: 8 September 2017

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




Related Items (23)

Game-theoretic frameworks for epidemic spreading and human decision-making: a reviewNonlinear Markov processes in big networksDiscrete-time control for systems of interacting objects with unknown random disturbance distributions: a mean field approachControl to Flocking of the Kinetic Cucker--Smale ModelNonlinear diffusions and stable-like processes with coefficients depending on the median or varStochastic Mitra-Wan forestry models analyzed as a mean field optimal control problemDistributed control of multi-agent systems with random parameters and a major agentOn the control of density-dependent stochastic population processes with time-varying behaviorModel-free mean-field reinforcement learning: mean-field MDP and mean-field Q-learningA mean field approach for optimization in discrete timeMean field Markov decision processesThe mean-field computation in a supermarket model with server multiple vacationsAn Overview for Markov Decision Processes in Queues and NetworksThe complexity of synchronizing Markov decision processesControl systems of interacting objects modeled as a game against nature under a mean field approachExtremal shift rule for continuous-time zero-sum Markov gamesMean-field-game model of corruptionA mean field capital accumulation game with HARA utilityA mean field absorbing control model for interacting objects systemsA mean field approach for discounted zero-sum games in a class of systems of interacting objectsMean Field Stochastic Games with Discrete States and Mixed PlayersApproximation and mean field control of systems of large populationsA limit theorem for Markov decision processes




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