Towards sample-efficient episodic control with DAC-ML

Autor:	Freire, Ismael T., Amil, Adrián F., Vouloutsi, Vasiliki, Verschure, Paul F. M. J.
Rok vydání:	2020
Předmět:	Computer Science - Artificial Intelligence Quantitative Biology - Neurons and Cognition Statistics - Machine Learning
Druh dokumentu:	Working Paper
Popis:	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. Recent studies have tried to overcome this limitation by adding memory systems and architectural biases to improve learning speed, such as in Episodic Reinforcement Learning. However, despite achieving incremental improvements, their performance is still not comparable to how humans learn behavioral policies. In this paper, we capitalize on the design principles of the Distributed Adaptive Control (DAC) theory of mind and brain to build a novel cognitive architecture (DAC-ML) that, by incorporating a hippocampus-inspired sequential memory system, can rapidly converge to effective action policies that maximize reward acquisition in a challenging foraging task. Comment: 8 pages, 3 figures
Databáze:	arXiv
Externí odkaz:	http://arxiv.org/abs/2012.13779 Zobrazit plný text záznamu View this record from Arxiv