On-Robot Policy Learning with O(2)-Equivariant SAC.

Dian Wang Mingxi Jia Xupeng Zhu Robin Walters Robert Platt

Published in: CoRR (2022)

Keyphrases

learning process
knowledge acquisition
goal directed
learning algorithm
mobile robot
autonomous robots
prior knowledge
skill learning
real time
reinforcement learning
online learning
unsupervised learning
path planning
learning problems
autonomous learning
motor skills