Title :
Convergence of critic-based training
Author :
Prokhorov, Dana V. ; Wunsch, Donald C., II
Author_Institution :
Dept. of Electr. Eng., Texas Tech. Univ., Lubbock, TX, USA
Abstract :
The paper discusses convergence issues when training adaptive critic designs (ACD) to control dynamic systems expressed as Markov sequences. We critically review two published convergence results of critic based training and propose to shift emphasis towards more practically valuable convergence proofs. We show a possible way to prove convergence of ACD training
Keywords :
Markov processes; adaptive systems; learning (artificial intelligence); neural nets; ACD training; Markov sequences; adaptive critic designs; convergence issues; convergence proofs; critic based training; dynamic systems control; neural networks; Adaptive control; Computational intelligence; Convergence; Costs; Counting circuits; Laboratories; Optimal control; Programmable control; Resonance light scattering; Symmetric matrices;
Conference_Titel :
Systems, Man, and Cybernetics, 1997. Computational Cybernetics and Simulation., 1997 IEEE International Conference on
Conference_Location :
Orlando, FL
Print_ISBN :
0-7803-4053-1
DOI :
10.1109/ICSMC.1997.633056
