2 papers
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…