Zero-shot sim-to-real transfer of tactile control policies for aggressive swing-up manipulation.

Thomas Bi Carmelo Sferrazza Raffaello D'Andrea

Published in: CoRR (2021)

Keyphrases

control policies
stochastic optimization problems
reinforcement learning
neural network
real world
optimal policy
action space
real time
learning algorithm
search algorithm
control system
dynamic environments
finite horizon