Model-free Consensus Maximization for Non-Rigid Shapes.

Thomas Probst Ajad Chhatkuli Danda Pani Paudel Luc Van Gool

Published in: ECCV (4) (2018)

Keyphrases

model free
reinforcement learning
reinforcement learning algorithms
function approximation
temporal difference
objective function
average reward
policy evaluation
data sets
learning environment
feature vectors
small number
impedance control