Parallel Q-Learning for a block-pushing problem

Laurent, Guillaume , Emmanuel Piat
Parallel Q-Learning for a block-pushing problem
Conference proceedings (pdf - 679KB)

Abstract: Our approach is based on reinforcement learning algorithm (Q-Learning). We propose an original architecture which realizes several learning processes at the same time. This method produces an almost optimal policy whatever the number of manipulated objects may be. Some simulations allowed us to optimize every parameter of the learning process. In particular, they show that the more objects there are, the faster the controller learns. The experimental tests show that, after the learning process, the controller fills his part perfectly.