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.
no code implementations • 5 Jul 2017 • Xerxes D. Arsiwalla, Pedro A. M. Mediano, Paul F. M. J. Verschure
Recent complexity measures such as integrated information have sought to operationalize this problem taking a whole-versus-parts perspective, wherein one explicitly computes the amount of information generated by a network as a whole over and above that generated by the sum of its parts during state transitions.
1 code implementation • 12 Jun 2017 • Clément Moulin-Frier, Tobias Fischer, Maxime Petit, Grégoire Pointeau, Jordi-Ysard Puigbo, Ugo Pattacini, Sock Ching Low, Daniel Camilleri, Phuong Nguyen, Matej Hoffmann, Hyung Jin Chang, Martina Zambelli, Anne-Laure Mealier, Andreas Damianou, Giorgio Metta, Tony J. Prescott, Yiannis Demiris, Peter Ford Dominey, Paul F. M. J. Verschure
This paper introduces a cognitive architecture for a humanoid robot to engage in a proactive, mixed-initiative exploration and manipulation of its environment, where the initiative can originate from both the human and the robot.
no code implementations • 5 Apr 2017 • Clément Moulin-Frier, Jordi-Ysard Puigbò, Xerxes D. Arsiwalla, Martì Sanchez-Fibla, Paul F. M. J. Verschure
In this paper, we argue that the future of Artificial Intelligence research resides in two keywords: integration and embodiment.