Search Results for author:
Found 19 papers, 6 papers with code
Discovering and Exploiting Sparse Rewards in a Learned Behavior Space
Learning optimal policies in sparse rewards settings is difficult as the learning agent has little to no feedback on the quality of its actions.
Sparse Reward Exploration via Novelty Search and Emitters
Contrary to existing emitters-based approaches, SERENE separates the search space exploration and reward exploitation into two alternating processes.
Emergence of Spatial Coordinates via Exploration
Spatial knowledge is a fundamental building block for the development of advanced perceptive and cognitive abilities.
Novelty Search makes Evolvability Inevitable
Evolvability is thus a natural byproduct of the search in this context.
Unsupervised Learning and Exploration of Reachable Outcome Space
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.
Unsupervised Emergence of Egocentric Spatial Structure from Sensorimotor Prediction
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.
Self-supervised Body Image Acquisition Using a Deep Neural Network for Sensorimotor Prediction
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.
Identification of Invariant Sensorimotor Structures as a Prerequisite for the Discovery of Objects
Our model is based on processing the unsupervised interaction of an artificial agent with its environment.
Grounding Perception: A Developmental Approach to Sensorimotor Contingencies
Sensorimotor contingency theory offers a promising account of the nature of perception, a topic rarely addressed in the robotics community.
A Non-linear Approach to Space Dimension Perception by a Naive Agent
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.
Learning an internal representation of the end-effector configuration space
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.
Learning agent's spatial configuration from sensorimotor invariants
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.
Grounding the Experience of a Visual Field through Sensorimotor Contingencies
The sensorimotor contingencies theory proposes to ground the development of those perceptive abilities in the way the agent can actively transform its sensory inputs.
Unsupervised Emergence of Spatial Structure from Sensorimotor Prediction
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.
Discovering space - Grounding spatial topology and metric regularity in a naive agent's sensorimotor experience
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.
Learning Representations of Spatial Displacement through Sensorimotor Prediction
Robots act in their environment through sequences of continuous motor commands.
A Sensorimotor Perspective on Grounding the Semantic of Simple Visual Features
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.
Grounding object perception in a naive agent's sensorimotor experience
Artificial object perception usually relies on a priori defined models and feature extraction algorithms.
Autonomous Grounding of Visual Field Experience through Sensorimotor Prediction
In a developmental framework, autonomous robots need to explore the world and learn how to interact with it.
