Real-Time Reinforcement Learning of Constrained Markov Decision Processes with Weak Derivatives

zbMath1294.90068arXiv1110.4946MaRDI QIDQ4925757

Felisa J. Vázquez-Abad, Vikram Krishnamurthy

Publication date: 12 June 2013

Full work available at URL: https://arxiv.org/abs/1110.4946

zbMATH Keywords

asymptotic biasstochastic approximation algorithmspherical coordinate parametrization

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

This page was built for publication: Real-Time Reinforcement Learning of Constrained Markov Decision Processes with Weak Derivatives