Using Convex Switching Techniques for Partially Observable Decision Processes

DOI10.1109/TAC.2015.2505403MaRDI QIDQ2980436zbMATH OpenOpenAlexFDO

Authors Juri Hinz

Publication date 3 May 2017

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

Full work available at URL https://doi.org/10.1109/tac.2015.2505403

Mathematics Subject Classification ID

Applications of Markov chains and discrete-time Markov processes on general state spaces (social mobility, learning theory, industrial processes, etc.) (60J20) Markov and semi-Markov decision processes (90C40)

Recommendations

• Technical Note—On the Convexity of Policy Regions in Partially Observed Systems
• A convex optimization approach to dynamic programming in continuous state and action spaces
• A convex analytic approach to Markov decision processes
• Optimal stochastic switching under convexity assumptions
• scientific article; zbMATH DE number 1786123
• Convex Optimization for Parameter Synthesis in MDPs
• Stochastic switching for partially observable dynamics and optimal asset allocation
• Policy Synthesis for Switched Linear Systems With Markov Decision Process Switching
• A useful technique for piecewise deterministic Markov decision processes
• A convex programming approach for discrete-time Markov decision processes under the expected total reward criterion

Cited in

(3)

• An algorithmic approach to optimal asset liquidation problems
• Technical Note—On the Convexity of Policy Regions in Partially Observed Systems
• Stochastic switching for partially observable dynamics and optimal asset allocation

This page was built for publication: Using Convex Switching Techniques for Partially Observable Decision Processes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q2980436)