A Proposal for Reducing the Number of Trial-and-Error Searches for Deep Q-Networks Combined with Exploitation-Oriented Learning

Naoki Kodama, Kazuteru Miyazaki, Taku Harada. A Proposal for Reducing the Number of Trial-and-Error Searches for Deep Q-Networks Combined with Exploitation-Oriented Learning. In M. Arif Wani, Mehmed Kantardzic, Moamar Sayed Mouchaweh, João Gama, Edwin Lughofer, editors, 17th IEEE International Conference on Machine Learning and Applications, ICMLA 2018, Orlando, FL, USA, December 17-20, 2018. pages 983-988, IEEE, 2018. [doi]

Abstract

Abstract is missing.