scientific article; zbMATH DE number 1086991

MaRDI QIDQ4363260zbMATH OpenFDO

Authors E. J. Collins

Publication date 18 December 1997

zbMATH Keywords

finite horizon Markov decision processesmanufacturingnonlinear rewardpenalty

Mathematics Subject Classification ID

Production models (90B30) Markov and semi-Markov decision processes (90C40)

Recommendations

• VARIANCE CONSTRAINED MARKOV DECISION PROCESS
• Finite-horizon dynamic optimisation when the terminal reward is a concave functional of the distribution of the final state
• Variance-Penalized Markov Decision Processes
• Constrained Discounted Dynamic Programming
• A convex analytic approach to Markov decision processes

Cited in

(2)

• Finite-horizon dynamic optimisation when the terminal reward is a concave functional of the distribution of the final state
• Risk-constrained reinforcement learning with percentile risk criteria

This page was built for publication:

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4363260)