Vague Neural Network Based Reinforcement Learning Control System for Inverted Pendulum
العنوان: | Vague Neural Network Based Reinforcement Learning Control System for Inverted Pendulum |
---|---|
المؤلفون: | Siwei Luo, Yibiao Zhao, Rui Fang, Liang Wang, Aidong Ma |
المصدر: | Neural Information Processing ISBN: 9783540464846 ICONIP (3) |
بيانات النشر: | Springer Berlin Heidelberg, 2006. |
سنة النشر: | 2006 |
مصطلحات موضوعية: | Computer Science::Machine Learning, Learning classifier system, Markov chain, Artificial neural network, business.industry, Q-learning, Decision problem, Machine learning, computer.software_genre, Inverted pendulum, Reinforcement learning, Artificial intelligence, Markov decision process, business, computer, Mathematics |
الوصف: | Reinforcement learning is a class of model-free learning control method that can solve Markov decision problems. But it has some problems in applications, especially in MDPs of continuous state spaces. In this paper, based on the vague neural networks, we propose a Q-learning algorithm which is comprehensively considering the reward and punishment of the environment. Simulation results in cart-pole balancing problem illustrate the effectiveness of the proposed method. |
ردمك: | 978-3-540-46484-6 |
الوصول الحر: | https://explore.openaire.eu/search/publication?articleId=doi_________::aac3a8ed15e58f2c146bef342b3d9e5fTest https://doi.org/10.1007/11893295_76Test |
رقم الانضمام: | edsair.doi...........aac3a8ed15e58f2c146bef342b3d9e5f |
قاعدة البيانات: | OpenAIRE |
ردمك: | 9783540464846 |
---|