Faster Deep Q-learning using Neural Episodic Control
Machine Learning
2018-06-05 v4 Artificial Intelligence
Abstract
The research on deep reinforcement learning which estimates Q-value by deep learning has been attracted the interest of researchers recently. In deep reinforcement learning, it is important to efficiently learn the experiences that an agent has collected by exploring environment. We propose NEC2DQN that improves learning speed of a poor sample efficiency algorithm such as DQN by using good one such as NEC at the beginning of learning. We show it is able to learn faster than Double DQN or N-step DQN in the experiments of Pong.
Keywords
Cite
@article{arxiv.1801.01968,
title = {Faster Deep Q-learning using Neural Episodic Control},
author = {Daichi Nishio and Satoshi Yamane},
journal= {arXiv preprint arXiv:1801.01968},
year = {2018}
}
Comments
6 pages, 6 figures, COMPSAC2018 short paper