Noise scheduling and out-of-distribution generalisation in deep reinforcement learning for 6-DOF robotic grasping
Abstract Exploration strategy is a fundamental but underexplored design choice in deep reinforcement learning for robotic manipulation. This paper presents a controlled empirical comparison of three off-policy configurations on a 6-DOF robotic grasping task using a Universal Robots UR5e in the RoboSuite simulation envi...
Ilija Mizhimakoski, Stefan Zlatinov, Hristijan Gjoreski et al.
· Scientific Reports · 0 citations