Reinforcement learning for long-run average cost.

DOI10.1016/S0377-2217(02)00874-3zbMath1102.90374MaRDI QIDQ1427588

Abhijit Gosavi

Publication date: 14 March 2004

Published in: European Journal of Operational Research (Search for Journal in Brave)

zbMATH Keywords

Stochastic processesReinforcement learningTwo time scales

Mathematics Subject Classification ID

Markov and semi-Markov decision processes (90C40)

Related Items

A reinforcement-learning approach for admission control in distributed network service systems, A policy gradient method for semi-Markov decision processes with application to call admission control, Reinforcement learning for joint pricing, lead-time and scheduling decisions in make-to-order systems, Reinforcement learning algorithms with function approximation: recent advances and applications, Approximate dynamic programming for capacity allocation in the service industry, Application of reinforcement learning to the game of Othello, Minimizing mean weighted tardiness in unrelated parallel machine scheduling with reinforcement learning, A performance-centred approach to optimising maintenance of complex systems, Look-ahead control of conveyor-serviced production station by using potential-based online policy iteration

Cites Work

• Unnamed Item
• Unnamed Item
• Unnamed Item
• Unnamed Item
• Optimal inspection policies for a manufacturing station
• Optimal control of diffusion processes with reflection
• Stochastic approximation methods for constrained and unconstrained systems
• Asynchronous stochastic approximation and Q-learning
• Stochastic approximation with two time scales
• Optimal control of a queueing network system with two types of customers
• Solving Semi-Markov Decision Problems Using Average Reward Reinforcement Learning
• Analysis of recursive stochastic algorithms
• Asynchronous Stochastic Approximations
• Stochastic Approximation for Nonexpansive Maps: Application to Q-Learning Algorithms
• Actor-Critic--Type Learning Algorithms for Markov Decision Processes
• The O.D.E. Method for Convergence of Stochastic Approximation and Reinforcement Learning
• A Stochastic Approximation Method
• The theory of dynamic programming