Search Results for author:
Found 7 papers, 2 papers with code
Purpose for Open-Ended Learning Robots: A Computational Taxonomy, Definition, and Operationalisation
Overall, the approach enables OEL robots to learn in an autonomous way but also to focus on acquiring goals and skills that meet the purposes of the designers and users.
DREAM Architecture: a Developmental Approach to Open-Ended Learning in Robotics
Robots are still limited to controlled conditions, that the robot designer knows with enough details to endow the robot with the appropriate models or behaviors.
How to reduce computation time while sparing performance during robot navigation? A neuro-inspired architecture for autonomous shifting between model-based and model-free learning
We present a novel arbitration mechanism between learning systems that explicitly measures performance and cost.
A Deep Learning Approach for Multi-View Engagement Estimation of Children in a Child-Robot Joint Attention task
In this work we tackle the problem of child engagement estimation while children freely interact with a robot in their room.
Prioritized Sweeping Neural DynaQ with Multiple Predecessors, and Hippocampal Replays
The Dyna reinforcement learning algorithms use off-line replays to improve learning.
Adaptive coordination of working-memory and reinforcement learning in non-human primates performing a trial-and-error problem solving task
We found that the behavior of the five monkeys was better explained in terms of a combination of RL and WM despite inter-individual differences.
Active exploration in parameterized reinforcement learning
We apply a meta-learning algorithm based on the comparison between variations of short-term and long-term reward running averages to simultaneously tune $\beta$ and the width of the Gaussian distribution from which continuous action parameters are drawn.
