Convergence of Dynamic Programming Models
From MaRDI portal
Publication:3960493
DOI10.1287/moor.6.4.493zbMath0496.90085OpenAlexW1985929135MaRDI QIDQ3960493
Publication date: 1981
Published in: Mathematics of Operations Research (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1287/moor.6.4.493
projectionscontinuous convergencediscretization proceduresdiscounted optimalitysequence of modelsweak conditionsinfinite stateapproximation of dynamic programming modelsassociated optimal value functionsassociated sets of optimal actionsupper-semi- continuous convergent sequences
Related Items (43)
Concepts of similarity for utility functions ⋮ A convex optimization approach to dynamic programming in continuous state and action spaces ⋮ Computable approximations for continuous-time Markov decision processes on Borel spaces based on empirical measures ⋮ On truncations and perturbations of Markov decision problems with an application to queueing network overflow control ⋮ Markov--Nash Equilibria in Mean-Field Games with Discounted Cost ⋮ A strategic market game with secured lending ⋮ Geometry of information structures, strategic measures and associated stochastic control topologies ⋮ Discretization procedures for adaptive Markov control processes ⋮ A distribution stability result for a stochastic optimal control problem ⋮ Near optimality of quantized policies in stochastic control under weak continuity conditions ⋮ Partially observed discrete-time risk-sensitive mean field games ⋮ Weak convergence of approximate solutions of stochastic equations with applications to random differential and integral equations∗ ⋮ Approximate Nash Equilibria in Partially Observed Stochastic Games with Mean-Field Interactions ⋮ Robustness to Incorrect System Models in Stochastic Control ⋮ Sequential stochastic control (single or multi-agent) problems nearly admit change of measures with independent measurement ⋮ The structure of extended real-valued metric spaces ⋮ A Universal Dynamic Program and Refined Existence Results for Decentralized Stochastic Control ⋮ Inflationary equilibrium in a stochastic economy with independent agents ⋮ Approximation of Markov decision processes with general state space ⋮ Discounted Continuous-Time Controlled Markov Chains: Convergence of Control Models ⋮ Markov decision processes ⋮ Some structured dynamic programs arising in economics ⋮ Convergence of partial maps ⋮ Completeness properties of the generalized compact-open topology on partial functions with closed domains ⋮ Vietoris topology on partial maps with compact domains ⋮ A continuity question of Dubins and Savage ⋮ Boundedly UC spaces and topologies on function spaces ⋮ Regularity and Stability of Feedback Relaxed Controls ⋮ Discrete-time average-cost mean-field games on Polish spaces ⋮ Approximate Markov-Nash Equilibria for Discrete-Time Risk-Sensitive Mean-Field Games ⋮ Unnamed Item ⋮ Unnamed Item ⋮ Robustness to Incorrect Priors in Partially Observed Stochastic Control ⋮ Comparison of Information Structures for Zero-Sum Games and a Partial Converse to Blackwell Ordering in Standard Borel Spaces ⋮ Complete metrizability of generalized compact-open topology ⋮ Stochastic approximations of constrained discounted Markov decision processes ⋮ A strategic market game with active bankruptcy ⋮ Approximation theory for stochastic variational and Ky Fan inequalities in finite dimensions ⋮ Čech-completeness and related properties of the generalized compact-open topology ⋮ Jointly continuous utility functions on submetrizable \(k_\omega\)-spaces ⋮ Approximations and bounds for a generalized optimal stopping problem ⋮ Robustness to incorrect models and data-driven learning in average-cost optimal stochastic control ⋮ A stability result for linear Markovian stochastic optimization problems
This page was built for publication: Convergence of Dynamic Programming Models
