This paper introduces learningprograms,an approximate dynamic programming(ADP) or otherwise named Neural Dynamic Programming(NDP) algorithm developed and tested by the *** programs are particularly suited for learnin...
详细信息
This paper introduces learningprograms,an approximate dynamic programming(ADP) or otherwise named Neural Dynamic Programming(NDP) algorithm developed and tested by the *** programs are particularly suited for learning based decision and control applications in both discrete and continuous state spaces, as demonstrated by our extensive examinations of both real life and artificial *** this paper,we first introduce the basic framework of our learningprograms,the associated learning algorithms,and then extensive case studies to demonstrate the effectiveness of our learning *** is probably the first time that neural dynamic programming type of learning algorithms has been applied to complex,real life continuous state problems. Until now,reinforcement learning(another learning approach for approximate dynamic programming) has been mostly successful in discrete state space *** the other hand,prior NDP based approaches to controlling continuous state space systems have all been limited to smaller,or linearized,or decoupled *** the work presented here compliments and advances the existing literature in the general area of learning approaches in approximate dynamic programming.
暂无评论