Approximate Dynamic Programming via a Smoothed Linear Program
From MaRDI portal
Publication:4648262
DOI10.1287/opre.1120.1044zbMath1251.90379arXiv0908.0506OpenAlexW2222696761MaRDI QIDQ4648262
Vijay V. Desai, Vivek Francis Farias, Ciamac Cyrus Moallemi
Publication date: 8 November 2012
Published in: Operations Research (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/0908.0506
optimizationlinear programmingMarkov decision processesstochastic controlapproximate dynamic programming
Related Items (9)
Approximate policy iteration: a survey and some new methods ⋮ New approximate dynamic programming algorithms for large-scale undiscounted Markov decision processes and their application to optimize a production and distribution system ⋮ Approximate linear programming for networks: average cost bounds ⋮ Relationship between least squares Monte Carlo and approximate linear programming ⋮ Shape constraints in economics and operations research ⋮ Network-Based Approximate Linear Programming for Discrete Optimization ⋮ Quadratic approximate dynamic programming for input‐affine systems ⋮ Data-driven optimal control with a relaxed linear program ⋮ Unnamed Item
This page was built for publication: Approximate Dynamic Programming via a Smoothed Linear Program