Sensorimotor contingencies as a key drive of development: from babies to robots
L Jacquey, G Baldassarre, VG Santucci… - Frontiers in …, 2019 - frontiersin.org
Much current work in robotics focuses on the development of robots capable of autonomous
unsupervised learning. An essential prerequisite for such learning to be possible is that the …
unsupervised learning. An essential prerequisite for such learning to be possible is that the …
GRAIL: A goal-discovering robotic architecture for intrinsically-motivated learning
VG Santucci, G Baldassarre… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
In this paper, we present goal-discovering robotic architecture for intrisically-motivated
learning (GRAIL), a four-level architecture that is able to autonomously: 1) discover changes …
learning (GRAIL), a four-level architecture that is able to autonomously: 1) discover changes …
Which is the best intrinsic motivation signal for learning multiple skills?
Humans and other biological agents are able to autonomously learn and cache different
skills in the absence of any biological pressure or any assigned task. In this respect, Intrinsic …
skills in the absence of any biological pressure or any assigned task. In this respect, Intrinsic …
A definition of open-ended learning problems for goal-conditioned agents
A lot of recent machine learning research papers have``open-ended learning''in their title.
But very few of them attempt to define what they mean when using the term. Even worse …
But very few of them attempt to define what they mean when using the term. Even worse …
Hierarchical reinforcement learning as creative problem solving
Although creativity is studied from philosophy to cognitive robotics, a definition has proven
elusive. We argue for emphasizing the creative process (the cognition of the creative agent) …
elusive. We argue for emphasizing the creative process (the cognition of the creative agent) …
A reinforcement learning architecture that transfers knowledge between skills when solving multiple tasks
P Tommasino, D Caligiore, M Mirolli… - IEEE Transactions on …, 2016 - ieeexplore.ieee.org
When humans learn several skills to solve multiple tasks, they exhibit an extraordinary
capacity to transfer knowledge between them. We present here the last enhanced version of …
capacity to transfer knowledge between them. We present here the last enhanced version of …
[HTML][HTML] Know your body through intrinsic goals
The firstobject'that newborn children play with is their own body. This activity allows them to
autonomously form a sensorimotor map of own body and a repertoire of actions supporting …
autonomously form a sensorimotor map of own body and a repertoire of actions supporting …
An embodied agent learning affordances with intrinsic motivations and solving extrinsic tasks with attention and one-step planning
G Baldassarre, W Lord, G Granato… - Frontiers in …, 2019 - frontiersin.org
We propose an architecture for the open-ended learning and control of embodied agents.
The architecture learns action affordances and forward models based on intrinsic …
The architecture learns action affordances and forward models based on intrinsic …
Phasic dopamine as a prediction error of intrinsic and extrinsic reinforcements driving both action acquisition and reward maximization: A simulated robotic study
An important issue of recent neuroscientific research is to understand the functional role of
the phasic release of dopamine in the striatum, and in particular its relation to reinforcement …
the phasic release of dopamine in the striatum, and in particular its relation to reinforcement …
From self-assessment to frustration, a small step toward autonomy in robotic navigation
A Jauffret, N Cuperlier, P Tarroux… - Frontiers in …, 2013 - frontiersin.org
Autonomy and self-improvement capabilities are still challenging in the fields of robotics and
machine learning. Allowing a robot to autonomously navigate in wide and unknown …
machine learning. Allowing a robot to autonomously navigate in wide and unknown …