Stochastic Approximate Scheduling by Neurodynamic Learning
| Authors: | Csáji Balázs Csanád, Computer and Automation Research Institute, Hungarian Academy of Sciences, Hungary
Monostori László, Computer and Automation Research Institute, Hungarian Academy of Sciences, Hungary |
|---|
| Topic: | 5.1 Manufacturing Plant Control |
|---|
| Session: | Advanced Manufacturing Plant Control |
|---|
| Keywords: | scheduling algorithms, machine learning, manufacturing systems, agents, Markov decision processes, neural networks, stochastic approximation |
|---|
Abstract
The paper suggests a stochastic approximate solution to scheduling problems with unrelated parallel machines. The presented method is based on neurodynamic programming (reinforcement learning and feed-forward artificial neural networks). For various scheduling environments (static-dynamic, deterministic-stochastic) different variants of episodic Q-learning rules are proposed. A way to improve the avoidance of local minima is also discussed. Some investigations on the exploration strategy, function approximation and parallelizing the solution are made. Finally, a few experimental results are shown.
