Please use this identifier to cite or link to this item:
|Title:||Receding horizon cache and extreme learning machine based reinforcement learning||Authors:||Shao, Zhifei
Er, Meng Joo
|Keywords:||DRNTU::Engineering::Electrical and electronic engineering||Issue Date:||2012||Source:||Shao, Z., Er, M. J., & Huang, G.-B. (2012). Receding Horizon Cache and Extreme Learning Machine Based Reinforcement Learning. 2012 12th International Conference on Control Automation Robotics & Vision (ICARCV), 1591-1596.||Abstract:||Function approximators have been extensively used in Reinforcement Learning (RL) to deal with large or continuous space problems. However, batch learning Neural Networks (NN), one of the most common approximators, has been rarely applied to RL. In this paper, possible reasons for this are laid out and a solution is proposed. Specifically, a Receding Horizon Cache (RHC) structure is designed to collect training data for NN by dynamically archiving state-action pairs and actively updating their Q-values, which makes batch learning NN much easier to implement. Together with Extreme Learning Machine (ELM), a new RL with function approximation algorithm termed as RHC and ELM based RL (RHC-ELM-RL) is proposed. A mountain car task was carried out to test RHC-ELM-RL and compare its performance with other algorithms.||URI:||https://hdl.handle.net/10356/97140
|DOI:||http://dx.doi.org/10.1109/ICARCV.2012.6485384||Rights:||© 2012 IEEE.||metadata.item.grantfulltext:||none||metadata.item.fulltext:||No Fulltext|
|Appears in Collections:||EEE Conference Papers|
Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.