Contextual Behaviors and Internal Representations Acquired by Reinforcement Learning with a Recurrent Neural Network in a Continuous State and Action Space Task-Reference-Cited by-同舟云学术

Contextual Behaviors and Internal Representations Acquired by Reinforcement Learning with a Recurrent Neural Network in a Continuous State and Action Space Task

Published:2009 Issue: Volume: Page:970-978
ISSN:0302-9743
Container-title:Advances in Neuro-Information Processing
language:
Short-container-title:

Author:

Utsunomiya Hiroki,Shibata Katsunari

Publisher

Springer Berlin Heidelberg

Link

http://link.springer.com/content/pdf/10.1007/978-3-642-03040-6_118

Reference9 articles.

1. Lin, L., Mitchell, T.M.: Memory Approaches to Reinforcement Learning In Non-Markovian Domains. Technical Report CMU-CS-TR-92-138, CMU, Computer Science (1992)

2. Onat, A., Kita, H., Nishikawa, Y.: Recurrent Neural Networks for Reinforcement Learning: Architecture, Learning Algorithms and Internal Representation. In: Proc. of IJCNN 1998, pp. 2010–2015 (1998)

3. Mizutani, E., Dreyfus, S.E.: Totally Model-Free Reinforcement Learning by Actor-Critic Elman Network in Non-Markovian Domains. In: Proc. of IJCNN 1998, pp. 2016–2021 (1998)

4. Onat, A., Kita, H., Nishikawa, Y.: Q-Learning with Recurrent Neural Networks as a Controller for the Inverted Pendulum Problem. In: Proc. of ICONIP 1998, pp. 837–840 (1998)

5. Bakker, B., Linaker, F., Schmidhuber, J.: Reinforcement Learning in Partially Observable Mobile Robot Domains Using Unsupervised Event Extraction. In: Proc. of IROS 2002, vol. 1, pp. 938–943 (2002)

Cited by 8 articles. 订阅此论文施引文献订阅此论文施引文献，注册后可以免费订阅5篇论文的施引文献，订阅后可以查看论文全部施引文献

1. Sensitivity – Local index to control chaoticity or gradient globally –;Neural Networks;2021-11

2. Q-learning with exploration driven by internal dynamics in chaotic neural network;2020 International Joint Conference on Neural Networks (IJCNN);2020-07

3. Acquisition of Context-Based Active Word Recognition by Q-Learning Using a Recurrent Neural Network;Robot Intelligence Technology and Applications 2;2014

4. Emergence of Discrete and Abstract State Representation through Reinforcement Learning in a Continuous Input Task;Advances in Intelligent Systems and Computing;2013

5. Emergence of Multi-step Discrete State Transition through Reinforcement Learning with a Recurrent Neural Network;Neural Information Processing;2012