✦ LIBER ✦

A three-network architecture for on-line learning and optimization based on adaptive dynamic programming

✍ Scribed by Haibo He; Zhen Ni; Jian Fu

Book ID: 113816769
Publisher: Elsevier Science
Year: 2012
Tongue: English
Weight: 783 KB
Volume: 78
Category: Article
ISSN: 0925-2312
DOI: 10.1016/j.neucom.2011.05.031

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

RETRACTED ARTICLE: A hierarchical learni

RETRACTED ARTICLE: A hierarchical learning architecture with multiple-goal representations and multiple timescale based on approximate dynamic programming

✍ Bo Liu, Shuai Li, Yuesheng Lou, Sanfeng Chen… 📂 Article 📅 2012 🏛 Springer-Verlag 🌐 English ⚖ 93 KB

Dynamic process programming for a roboti

Dynamic process programming for a robotic manipulator based on hopfield NN monotonous optimization searching

✍ Yu, Zhongwei ;Chen, Huitang ;Woo, Peng-Yung 📂 Article 📅 2004 🏛 John Wiley and Sons 🌐 English ⚖ 130 KB

[IEEE 2009 IEEE Symposium on Adaptive Dy

[IEEE 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) - Nashville, TN, USA (2009.03.30-2009.04.2)] 2009 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning - Algorithms for variance reduction in a policy-gradient based actor-critic framework

✍ Awate, Yogesh P. 📂 Article 📅 2009 🏛 IEEE ⚖ 806 KB

[IEEE 2013 IEEE Symposium on Adaptive Dy

[IEEE 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) - Singapore, Singapore (2013.04.16-2013.04.19)] 2013 IEEE Symposium on Adaptive Dynamic Programming and Reinforcement Learning (ADPRL) - Adaptive optimal control for nonlinear discrete-time systems

✍ Qin, Chunbin; Zhang, Huaguang; Luo, Yanhong 📂 Article 📅 2013 🏛 IEEE ⚖ 185 KB

On design of a survivable network archit

On design of a survivable network architecture for dynamic routing: Optimal solution strategy and an efficient heuristic

✍ Iradj Ouveysi; Andrew Wirth 📂 Article 📅 1999 🏛 Elsevier Science 🌐 English ⚖ 262 KB

We investigate network planning and design under volatile conditions of link failures and trac overload. Our model is a non-simultaneous multi-commodity problem, with any particular two link failure being considered as one scenario. We show that the optimal solution model is not practically solvable

A Dynamic Feedforward Neural Network Bas

A Dynamic Feedforward Neural Network Based on Gaussian Particle Swarm Optimization and its Application for Predictive Control

✍ Min Han, ; Jianchao Fan, ; Jun Wang, 📂 Article 📅 2011 🏛 IEEE 🌐 English ⚖ 761 KB