scientific article; zbMATH DE number 5957388

MaRDI QIDQ3174029zbMATH OpenFDO

Authors Shalabh Bhatnagar, Vivek Borkar, Madhukar Akarapu

Publication date 12 October 2011

Full work available at URL http://www.jmlr.org/papers/v7/bhatnagar06a.html

zbMATH Keywords

Markov decision processesreinforcement learningoptimal control conditioned on a rare eventsimulation based algorithmsSPSA with deterministic perturbations

Mathematics Subject Classification ID

Markov chains (discrete-time Markov processes on discrete state spaces) (60J10) Stochastic systems in control theory (general) (93E03)

Recommendations

• Ergodic control of partially observed Markov chains
• Ergodic control of partially observed Markov processes with equivalent transition probabilities
• Ergodic Control of Markov Chains with Constraints—the General Case
• Ergodic Control of Continuous-Time Markov Chains with Pathwise Constraints
• An approximation approach to ergodic semi-Markov control processes
• Approximating Ergodic Average Reward Continuous-Time Controlled Markov Chains
• A partially observed control problem for Markov chains

Cited in

(2)

• Risk-Sensitive Reinforcement Learning via Policy Gradient Search
• Performance analysis conditioned on rare events: an adaptive simulation scheme

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 Q3174029)