Transferring optimal contact skills to flexible manipulators by reinforcement learning.

Wenjun Xu Anqi Pan Hongliang Ren

Published in: Int. J. Intell. Robotics Appl. (2019)

Keyphrases

reinforcement learning
transfer learning
optimal control
dynamic programming
adaptive control
neural network
learning algorithm
function approximation
control policy
information systems
multi agent
degrees of freedom
learning environment
markov decision processes
learning tasks
optimal design