no code implementations • 29 Dec 2021 • Ismael T. Freire, Adrián F. Amil, Paul F. M. J. Verschure
Here, we demonstrate that including a bias in the acquired memory content derived from the order of episodic sampling improves both the sample and memory efficiency of an episodic control algorithm.
no code implementations • 26 Dec 2020 • Ismael T. Freire, Adrián F. Amil, Vasiliki Vouloutsi, Paul F. M. J. Verschure
The sample-inefficiency problem in Artificial Intelligence refers to the inability of current Deep Reinforcement Learning models to optimize action policies within a small number of episodes.