Login / Signup
Learning Multi-step Robotic Manipulation Policies from Visual Observation of Scene and Q-value Predictions of Previous Action.
Sulabh Kumra
Shirin Joshi
Ferat Sahin
Published in:
CoRR (2022)
Keyphrases
</>
multi step
video sequences
learning process
d scene
visual information
mobile robot
reinforcement learning
single image
learning algorithm
lower bound
active learning
robotic systems