3 papers
cs.LG2022
Robot Policy Learning from Demonstration Using Advantage Weighting and Early Termination
Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayahuitl
Learning robotic tasks in the real world is still highly challenging and effective practical solutions remain to be found. Traditional methods used in this area are imitation learn…
cs.RO2021
A Study on Dense and Sparse (Visual) Rewards in Robot Policy Learning
Abdalkarim Mohtasib, Gerhard Neumann, Heriberto Cuayahuitl
Deep Reinforcement Learning (DRL) is a promising approach for teaching robots new behaviour. However, one of its main limitations is the need for carefully hand-coded reward signal…
cs.RO2021
Neural Task Success Classifiers for Robotic Manipulation from Few Real Demonstrations
Abdalkarim Mohtasib, Amir Ghalamzan E., Nicola Bellotto +1
Robots learning a new manipulation task from a small amount of demonstrations are increasingly demanded in different workspaces. A classifier model assessing the quality of actions…