output
20152021
most citedDisCoRL: Continual Reinforcement Learning via Policy Distillation

35 citations

7 papers

cs.RO20211 cited

DREAM Lite: Simplifying Robot Assisted Therapy for ASD

Alexandre Mazel, Silviu Matu

Robot-Assisted Therapy (RAT) has successfully been used to improve social skills in children with autism spectrum disorders (ASD). The DREAM project explores how to deliver effecti…

cs.NE20219 cited

Sparse Reward Exploration via Novelty Search and Emitters

Giuseppe Paolo, Alexandre Coninx, Stephane Doncieux +1

Reward-based optimization algorithms require both exploration, to find rewards, and exploitation, to maximize performance. The need for efficient exploration is even more significa…

cs.RO20211 cited

Target Reaching Behaviour for Unfreezing the Robot in a Semi-Static and Crowded Environment

Arturo Cruz-Maya

Robot navigation in human semi-static and crowded environments can lead to the freezing problem, where the robot can not move due to the presence of humans standing on its path and…

eess.SY20216 cited

Interval centred form for proving stability of non-linear discrete-time systems

Auguste Bourgois, Luc Jaulin

In this paper, we propose a new approach to prove stability of non-linear discrete-time systems. After introducing the new concept of stability contractor, we show that the interva…

cs.LG2020

Emergence of Spatial Coordinates via Exploration

Alban Laflaquière

Spatial knowledge is a fundamental building block for the development of advanced perceptive and cognitive abilities. Traditionally, in robotics, the Euclidean (x,y,z) coordinate s…

cs.LG201935 cited

DisCoRL: Continual Reinforcement Learning via Policy Distillation

René Traoré, Hugo Caselles-Dupré, Timothée Lesort +4

In multi-task reinforcement learning there are two main challenges: at training time, the ability to learn different policies with a single model; at test time, inferring which of…