Ordinary Differential Equation Methods for Markov Decision Processes and Application to Kullback--Leibler Control Cost
From MaRDI portal
Publication:4602532
DOI10.1137/16M1100204zbMath1388.90122arXiv1605.04591WikidataQ115246950 ScholiaQ115246950MaRDI QIDQ4602532
Publication date: 12 February 2018
Published in: SIAM Journal on Control and Optimization (Search for Journal in Brave)
Full work available at URL: https://arxiv.org/abs/1605.04591
Computational methods in Markov chains (60J22) Optimality conditions and duality in mathematical programming (90C46) Optimal stochastic control (93E20) Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Stochastic learning and adaptive control (93E35) Markov and semi-Markov decision processes (90C40)
Related Items
Kullback–Leibler-Quadratic Optimal Control, Sparse randomized shortest paths routing with Tsallis divergence regularization
Cites Work
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Unnamed Item
- Towards fully probabilistic control design
- Stochastic optimal control. The discrete time case
- Large deviations asymptotics and the spectral theory of multiplicatively regular Markov proces\-ses
- Spectral theory and limit theorems for geometrically ergodic Markov processes
- Ensemble control of cycling energy loads: Markov decision approach
- Linear Programming and Sequential Decisions
- Rationally Inattentive Control of Markov Processes
- Ancillary Service to the Grid Using Intelligent Deferrable Loads
- Online Markov Decision Processes With Kullback–Leibler Control Cost
- Efficient computation of optimal actions
- General Irreducible Markov Chains and Non-Negative Operators
- Markov Chains and Stochastic Stability
- Optimal Control and Nonlinear Filtering for Nondegenerate Diffusion Processes
- Perturbation theory and finite Markov chains
- Certain Inequalities in Information Theory and the Cramer-Rao Inequality
