1 code implementation • 2 Nov 2021 • Giuseppe Paolo, Miranda Coninx, Alban Laflaquière, Stephane Doncieux
Learning optimal policies in sparse rewards settings is difficult as the learning agent has little to no feedback on the quality of its actions.
1 code implementation • 5 Feb 2021 • Giuseppe Paolo, Alexandre Coninx, Stephane Doncieux, Alban Laflaquière
Contrary to existing emitters-based approaches, SERENE separates the search space exploration and reward exploitation into two alternating processes.
no code implementations • 29 Oct 2020 • Alban Laflaquière
Spatial knowledge is a fundamental building block for the development of advanced perceptive and cognitive abilities.
2 code implementations • 13 May 2020 • Stephane Doncieux, Giuseppe Paolo, Alban Laflaquière, Alexandre Coninx
Evolvability is thus a natural byproduct of the search in this context.
1 code implementation • 12 Sep 2019 • Giuseppe Paolo, Alban Laflaquière, Alexandre Coninx, Stephane Doncieux
Results show that TAXONS can find a diverse set of controllers, covering a good part of the ground-truth outcome space, while having no information about such space.
1 code implementation • NeurIPS 2019 • Alban Laflaquière, Michael Garcia Ortiz
Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood.
1 code implementation • 3 Jun 2019 • Alban Laflaquière, Verena V. Hafner
This work investigates how a naive agent can acquire its own body image in a self-supervised way, based on the predictability of its sensorimotor experience.
no code implementations • 11 Oct 2018 • Nicolas Le Hir, Olivier Sigaud, Alban Laflaquière
Our model is based on processing the unsupervised interaction of an artificial agent with its environment.
no code implementations • 3 Oct 2018 • Alban Laflaquière, Nikolas Hemion, Michaël Garcia Ortiz, Jean-Christophe Baillie
Sensorimotor contingency theory offers a promising account of the nature of perception, a topic rarely addressed in the robotics community.
no code implementations • 3 Oct 2018 • Alban Laflaquière, Sylvain Argentieri, Olivia Breysse, Stéphane Genet, Bruno Gas
A new approach is to consider perception as an experimentally acquired ability that is learned exclusively through the analysis of the agent's sensorimotor flow.
no code implementations • 3 Oct 2018 • Alban Laflaquière, Alexander V. Terekhov, Bruno Gas, J. Kevin O'Regan
Current machine learning techniques proposed to automatically discover a robot kinematics usually rely on a priori information about the robot's structure, sensors properties or end-effector position.
no code implementations • 3 Oct 2018 • Alban Laflaquière, J. Kevin O'Regan, Sylvain Argentieri, Bruno Gas, Alexander V. Terekhov
We show that the notion of space as environment-independent cannot be deduced solely from exteroceptive information, which is highly variable and is mainly determined by the contents of the environment.
no code implementations • 3 Oct 2018 • Alban Laflaquière
The sensorimotor contingencies theory proposes to ground the development of those perceptive abilities in the way the agent can actively transform its sensory inputs.
no code implementations • 2 Oct 2018 • Alban Laflaquière, Michael Garcia Ortiz
Despite its omnipresence in robotics application, the nature of spatial knowledge and the mechanisms that underlie its emergence in autonomous agents are still poorly understood.
no code implementations • 7 Jun 2018 • Alban Laflaquière, J. Kevin O'Regan, Bruno Gas, Alexander Terekhov
We here show that the structure of space can be autonomously discovered by a naive agent in the form of sensorimotor regularities, that correspond to so called compensable sensory experiences: these are experiences that can be generated either by the agent or its environment.
no code implementations • 16 May 2018 • Michael Garcia Ortiz, Alban Laflaquière
Robots act in their environment through sequences of continuous motor commands.
no code implementations • 11 May 2018 • Alban Laflaquière
Without any a priori knowledge about the way its sensorimotor information is encoded, we show how an agent can characterize the uniformity and edge-ness of the visual features it interacts with.
no code implementations • 26 Sep 2016 • Alban Laflaquière, Nikolas Hemion
Artificial object perception usually relies on a priori defined models and feature extraction algorithms.
no code implementations • 3 Aug 2016 • Alban Laflaquière
In a developmental framework, autonomous robots need to explore the world and learn how to interact with it.