Actor-critic algorithms for hierarchical Markov decision processes

DOI10.1016/j.automatica.2005.12.010zbMath1102.93043OpenAlexW2027220971MaRDI QIDQ856510

J. Ranjan Panigrahi, Shalabh Bhatnagar

Publication date: 7 December 2006

Published in: Automatica (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.automatica.2005.12.010

zbMATH Keywords

optimal controllearning algorithmsMarkov decision processesstochastic approximationhierarchical decision making

Mathematics Subject Classification ID

Optimal stochastic control (93E20) Stochastic learning and adaptive control (93E35) Stochastic systems in control theory (general) (93E03)

Related Items

Reinforcement learning based algorithms for average cost Markov decision processes

Cites Work

• Unnamed Item
• Unnamed Item
• A one-measurement form of simultaneous perturbation stochastic approximation
• Asynchronous stochastic approximation and Q-learning
• Between MDPs and semi-MDPs: A framework for temporal abstraction in reinforcement learning
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• Multilayer control of large Markov chains
• OnActor-Critic Algorithms
• Two-timescale simultaneous perturbation stochastic approximation using deterministic perturbation sequences
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Multitime scale markov decision processes
• A Simultaneous Perturbation Stochastic Approximation-Based Actor–Critic Algorithm for Markov Decision Processes