APPLICATION OF HIERARCHICAL REINFORCEMENT LEARNING IN ENGINEERING DOMAIN

1.Introduction Reinforcement learning(RL)is the problem of generating optimal actions given the opportunity of interacting with environment(Sutton and Barto1998).The algorithm solving RL is called RL algorithm,which can provide solutions to very large-scale optimal control problems.It has achieved many successful applications in engineering(Mataric1997,Crites and Barto1996,Rajbala and Sridher et al.2001,Mahadevan and Sridher et al.1997,Zhang1996).However,conventional RL system is restr…

Application of hierarchical reinforcement learning in engineering domain

The slow convergence rate of reinforcement learning algorithms limits their wider application. In engineering domains, hierarchical reinforcement learning is developed to perform actions temporally according to prior knowledge. This system can converge fast due to reduced state space. There is a test of elevator group control to show the power of the new system. Two conventional group control algorithms are adopted as prior knowledge. Performance indicates that hierarchical reinforcement learning can reduce the learning time dramatically.