V-D D3QN: the Variant of Double Deep Q-Learning Network with Dueling Architecture
Authors:
- Ying HuangYHYing Huang
- GuoLiang WeiGWGuoLiang Wei
- YongXiong WangYWYongXiong Wang
- 1 July 2018
- conference paper
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 9130-9135
Abstract
No abstract availableThis publication has 3 references indexed in Scilit:
- Human-level control through deep reinforcement learningNature, 2015
- Algorithms for Reinforcement LearningSynthesis Lectures on Artificial Intelligence and Machine Learning, 2010
- Q-learningMachine Learning, 1992