An actor-critic algorithm for constrained Markov decision processes

DOI10.1016/j.sysconle.2004.08.007zbMath1129.90322MaRDI QIDQ2504518

Vivek S. Borkar

Publication date: 25 September 2006

Published in: Systems \& Control Letters (Search for Journal in Brave)

Full work available at URL: https://doi.org/10.1016/j.sysconle.2004.08.007

zbMATH Keywords

stochastic approximation; reinforcement learning; envelope theorem; actor-critic algorithms; constrained Markov decision processes

Mathematics Subject Classification ID

90B40: Search theory

91B70: Stochastic models in economics

91B62: Economic growth models

Related Items

Risk-Constrained Reinforcement Learning with Percentile Risk Criteria, Finite-Time Analysis and Restarting Scheme for Linear Two-Time-Scale Stochastic Approximation, Risk-Sensitive Reinforcement Learning via Policy Gradient Search, Optimal Distributed Uplink Channel Allocation: A Constrained MDP Formulation, Dimension reduction based adaptive dynamic programming for optimal control of discrete-time nonlinear control-affine systems, Safety-constrained reinforcement learning with a distributional safety critic, An online actor-critic algorithm with function approximation for constrained Markov decision processes, Quasi-Newton smoothed functional algorithms for unconstrained and constrained simulation optimization, An actor-critic algorithm with function approximation for discounted cost constrained Markov decision processes, A new learning algorithm for optimal stopping, Variance-constrained actor-critic algorithms for discounted and average reward MDPs, Approachability in Stackelberg stochastic games with vector costs, Delay-aware online service scheduling in high-speed railway communication systems, Whittle index based Q-learning for restless bandits with average reward, A note on linear function approximation using random projections, Opportunistic Transmission over Randomly Varying Channels

Cites Work

• Stochastic approximation with two time scales
• An analysis of temporal-difference learning with function approximation
• OnActor-Critic Algorithms
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• Envelope Theorems for Arbitrary Choice Sets
• Optimal control and viscosity solutions of Hamilton-Jacobi-Bellman equations
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item