Actor-Critic Algorithms with Online Feature Adaptation

DOI10.1145/2868723zbMath1369.90190OpenAlexW2256989395MaRDI QIDQ5270681

Vivek S. Borkar, K. J. Prabuchandran, Shalabh Bhatnagar

Publication date: 30 June 2017

Published in: ACM Transactions on Modeling and Computer Simulation (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1145/2868723

zbMATH Keywords

Markov decision processesstochastic approximationonline learningGrassmann manifoldtemporal difference learningactor-critic algorithmsfunction approximationSPSApolicy gradientsfeature adaptationresidual gradient scheme

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items (1)

Full Gradient DQN Reinforcement Learning: A Provably Convergent Scheme

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Stochastic recursive algorithms for optimization. Simultaneous perturbation methods
• Stochastic approximation. A dynamical systems viewpoint.
• Natural actor-critic algorithms
• Stochastic approximation methods for constrained and unconstrained systems
• Stochastic approximation with two time scales
• Average cost temporal-difference learning
• Convergence rate of linear two-time-scale stochastic approximation.
• Basis function adaptation in temporal difference reinforcement learning
• Multivariate stochastic approximation using a simultaneous perturbation gradient approximation
• The Geometry of Algorithms with Orthogonality Constraints
• An analysis of temporal-difference learning with function approximation
• OnActor-Critic Algorithms
• Simulation-based optimization of Markov reward processes
• 10.1162/1532443041827934
• 10.1162/1532443041827907

This page was built for publication: Actor-Critic Algorithms with Online Feature Adaptation