✦ LIBER ✦

Stable reinforcement learning with recurrent neural networks

✍ Scribed by James Nate Knight; Charles Anderson

Book ID: 107504867
Publisher: South China University of Technology and Academy of Mathematics and Systems Science, CAS
Year: 2011
Tongue: English
Weight: 375 KB
Volume: 9
Category: Article
ISSN: 1672-6340
DOI: 10.1007/s11768-011-0177-1

No coin nor oath required. For personal study only.

📜 SIMILAR VOLUMES

Reinforcement learning of dynamic behavi

Reinforcement learning of dynamic behavior by using recurrent neural networks

✍ Ahmet Onat; Hajime Kita; Yoshikazu Nishikawa 📂 Article 📅 1997 🏛 Springer Japan 🌐 English ⚖ 411 KB

Learning in recurrent neural networks

✍ Halbert White 📂 Article 📅 1991 🏛 Elsevier Science 🌐 English ⚖ 85 KB

Robust stability of recurrent neural net

Robust stability of recurrent neural networks with ISS learning algorithm

✍ Choon Ki Ahn 📂 Article 📅 2010 🏛 Springer Netherlands 🌐 English ⚖ 434 KB

A realtime learning algorithm for recurr

A realtime learning algorithm for recurrent neural networks

✍ Tadasu Uchiyama; Katsunori Shimohara 📂 Article 📅 1991 🏛 John Wiley and Sons 🌐 English ⚖ 438 KB

Effective learning in recurrent max–min

Effective learning in recurrent max–min neural networks

✍ Loo-Nin Teow; Kia-Fock Loe 📂 Article 📅 1998 🏛 Elsevier Science 🌐 English ⚖ 208 KB

Max and min operations have interesting properties that facilitate the exchange of information between the symbolic and real-valued domains. As such, neural networks that employ max-min activation functions have been a subject of interest in recent years. Since max-min functions are not strictly dif

Improving reinforcement learning in stoc

Improving reinforcement learning in stochastic RAM-based neural networks

✍ Alistair Ferguson; Hamid Bolouri 📂 Article 📅 1996 🏛 Springer US 🌐 English ⚖ 250 KB

RAM-based neural networks are designed to be efficiently implemented in hardware. The desire to retain this property influences the training algorithms used, and has led to the use of reinforcement (reward-penalty) learning. An analysis of the reinforcement algorithm applied to RAM-based nodes has s