共 10 条
- [1] Training Strategies for Critic and Action Neural Networks in Dual Heuristic Programming Method. Lendaris G G,Paintz C. Proc. of the IEEE International Conference on Neural Networks . 1997
- [2] A menu of designs for reinforcement learningover time,in neural networks for control. Werbos P J. MIT Press . 1990
- [3] ε-adaptive dynamic programming for discrete-time systems. Liu D,Jin N. Proceedings of the IEEE International Joint Conference on Neural Networks . 2008
- [4] On-line learning control by association and reinforcement. Si J, Wang Y T. IEEE Transactions on Neural Networks . 2001
- [5] Adaptive Critic Designs. Prokhorov D V,Wunsch D C. IEEE Transactions on Neural Networks . 1997
- [6] Adaptive dynamicprogramming for finite-horizon optimal control of discrete-time nonlinear systems withε-error bound. Wang F Y,Jin N,Liu D R,et al. IEEE Transactions on Neural Networks . 2010
- [7] Finite horizon discrete-time approximatedynamic programming. Liu D R,Jin N. Proc of the 2006 IEEE IntSymposium on Intelligent Control . 2006
- [8] A novel infinite-time optimal tracking control scheme for a class ofdiscrete-time nonlinear systems via the greedy HDPiteration algorithm. Zhang H G,Wei Q L,Luo Y H. IEEE Trans on Systems,Man andCybernetics . 2008
- [9] Adaptive dynamic programming fordiscrete-time systems with infinite horizon andε-errorbound in the performance cost. Liu D R,Jin N. Proc of Int Joint Confon Neural Networks . 2009
- [10] Discrete-time non-linear HJB solution using approximate dynamic programming:con-vergence proof. TAMIMI A A,LEWIS F L,ABU-KHALAF M. IEEE Transactions on Systems,Man, and Cyber-netics,part B:Cybernetics . 2008