Look-ahead control of conveyor-serviced production station by using potential-based online policy iteration
DOI10.1080/00207170902823006zbMath1178.93147OpenAlexW2037323358MaRDI QIDQ3654586
Publication date: 6 January 2010
Published in: International Journal of Control (Search for Journal in Brave)
Full work available at URL: https://doi.org/10.1080/00207170902823006
explorationperformance potentiallook-ahead controlpolicy iteration (PI)semi-Markov decision process (SMDP)conveyor-serviced production station (CSPS)
Learning and adaptive systems in artificial intelligence (68T05) Production models (90B30) Optimal stochastic control (93E20) Empirical decision procedures; empirical Bayes procedures (62C12)
Related Items (1)
Cites Work
- A policy gradient method for semi-Markov decision processes with application to call admission control
- The analysis of a conveyor-serviced production station
- Reinforcement learning for long-run average cost.
- A reinforcement learning algorithm based on policy iteration for average reward: Empirical results with yield management and convergence analysis
- Simulation-based optimization: Parametric optimization techniques and reinforcement learning
- Learning Algorithms for Markov Decision Processes with Average Cost
- Solving Semi-Markov Decision Problems Using Average Reward Reinforcement Learning
- Error bounds of optimization algorithms for semi-Markov decision processes
- The Optimal Look-Ahead Policy for Admission to a Single Server System
- Successive approximation approach of optimal control for nonlinear discrete-time systems
- CSPS model: Look-ahead controls and physics
- Potential-Based Online Policy Iteration Algorithms for Markov Decision Processes
This page was built for publication: Look-ahead control of conveyor-serviced production station by using potential-based online policy iteration
