Login / Signup
Efficient reinforcement learning with least-squares soft Bellman residual for robotic grasping.
Yixing Lan
Junkai Ren
Tao Tang
Xin Xu
Yifei Shi
Zixin Tang
Published in:
Robotics Auton. Syst. (2023)
Keyphrases
</>
least squares
bellman residual
policy evaluation
policy iteration
reinforcement learning
sample path
markov decision processes
asymptotic analysis
function approximation
model free
optical flow
temporal difference
multi agent
vision system
optimal policy
object manipulation
learning algorithm