Model-free Probabilistic Movement Primitives for physical interaction.

Alexandros Paraschos Elmar Rueckert Jan Peters Gerhard Neumann

Published in: IROS (2015)

Keyphrases

model free
reinforcement learning
reinforcement learning algorithms
function approximation
temporal difference
bayesian networks
physical world
probabilistic model
policy iteration
policy evaluation
generative model
average reward
artificial neural networks
human robot interaction