Multi-source transfer ELM-based Q learning
作者： Jie Pan , Xuesong Wang , Yuhu Cheng , Ge Cao
DOI: 10.1016/J.NEUCOM.2013.04.045
关键词:
摘要: … even lead to negative transfer. To solve this problem, we proposed a multi-source transfer learning technology and applied it to the ELM-based Q learning. In our study, the proposed Q …
sci-hub.se 
researchgate.net 参考文章(26)
Kurt Driessens, Tom Croonenborghs, Jan Ramon, Transfer learning for reinforcement learning through goal and policy parametrization international conference on machine learning. pp. 1- 4 ,(2006)
Tom Croonenborghs, Kurt Driessens, Maurice Bruynooghe, Learning relational options for inductive transfer in relational reinforcement learning inductive logic programming. ,vol. 4894, pp. 88- 97 ,(2007) , 10.1007/978-3-540-78469-2_12
Fernando Fernández, Policy Reuse for Transfer Learning Across Tasks with Different State and Action Spaces ,(2006)
Andrew G. Barto, Marc Pickett, PolicyBlocks: An Algorithm for Creating Useful Macro-Actions in Reinforcement Learning international conference on machine learning. pp. 506- 513 ,(2002)
Huang Deshuang, Ma Songde, A new radial basis probabilistic neural network model international conference on signal processing. ,vol. 2, pp. 1449- 1452 ,(1996) , 10.1109/ICSIGP.1996.571134
José Antonio Martín H, Javier de Lope, Darío Maravall, Robust high performance reinforcement learning through weighted k-nearest neighbors Neurocomputing. ,vol. 74, pp. 1251- 1259 ,(2011) , 10.1016/J.NEUCOM.2010.07.027
De-Shuang Huang, The united adaptive learning algorithm for the link weights and shape parameter in RBFN for pattern recognition International Journal of Pattern Recognition and Artificial Intelligence. ,vol. 11, pp. 873- 888 ,(1997) , 10.1142/S0218001497000391
Hesam Montazeri, Sajjad Moradi, Reza Safabakhsh, Continuous state/action reinforcement learning: A growing self-organizing map approach Neurocomputing. ,vol. 74, pp. 1069- 1082 ,(2011) , 10.1016/J.NEUCOM.2010.11.012
Shi-chao Wang, Zheng-xi Song, Hao Ding, Hao-bin Shi, An Improved Reinforcement Q-Learning Method with BP Neural Networks in Robot Soccer 2011 Fourth International Symposium on Computational Intelligence and Design. ,vol. 1, pp. 177- 180 ,(2011) , 10.1109/ISCID.2011.53
Michael G. Madden, Tom Howley, Transfer of Experience Between Reinforcement Learning Environments with Progressive Difficulty Artificial Intelligence Review. ,vol. 21, pp. 375- 398 ,(2004) , 10.1023/B:AIRE.0000036264.95672.64