Please use this identifier to cite or link to this item:
http://hdl.handle.net/2445/182959
Title: | Towards sample-efficient policy learning with DAC-ML |
Author: | Freire, Ismael T. Amil, Adrián F. Vouloutsi, Vasiliki Verschure, Paul F. M. J. |
Keywords: | Aprenentatge automàtic Presa de decisions Machine learning Decision making |
Issue Date: | 1-Jul-2021 |
Publisher: | Elsevier B.V. |
Abstract: | 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. |
Note: | Reproducció del document publicat a: https://doi.org/10.1016/j.procs.2021.06.035 |
It is part of: | Procedia Computer Science, 2021, vol 190, p. 256-262 |
URI: | http://hdl.handle.net/2445/182959 |
Related resource: | https://doi.org/10.1016/j.procs.2021.06.035 |
ISSN: | Freire IT;Amil AF;Vouloutsi V;Verschure PFMJ. Towards sample-efficient policy learning with DAC-ML. Procedia Computer Science, 2021, 190, 256-262 1877-0509 |
Appears in Collections: | Articles publicats en revistes (Institut de Bioenginyeria de Catalunya (IBEC)) |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
1-s2.0-S1877050921012795-main.pdf | 958.17 kB | Adobe PDF | View/Open |
This item is licensed under a
Creative Commons License