Model-free human-like humanoid push recovery.

Noel Maalouf Imad H. Elhajj Daniel C. Asmar Elie A. Shammas

Published in: ROBIO (2015)

Keyphrases

model free
reinforcement learning
function approximation
reinforcement learning algorithms
temporal difference
humanoid robot
policy iteration
human robot interaction
dynamic programming
sufficient conditions
machine learning algorithms
average reward
policy evaluation