Faster Deep Q-learning using Neural Episodic Control
The Research on deep reinforcement learning to estimate Q-value by deep learning has been active in recent years. In deep reinforcement learning, it is important to efficiently learn the experiences that a agent has collected by exploring the environment. In this research, we propose NEC2DQN that improves learning speed of a algorithm with poor sample efficiency by using a algorithm with good one at the beginning of learning, and we demonstrate it in experiments.
READ FULL TEXT