slimIPL: Language-Model-Free Iterative Pseudo-Labeling.

Tatiana Likhomanenko Qiantong Xu Jacob Kahn Gabriel Synnaeve Ronan Collobert

Published in: Interspeech (2021)

Keyphrases

model free
reinforcement learning
function approximation
temporal difference
reinforcement learning algorithms
policy iteration
natural language
impedance control
data sets
active learning
programming language
machine learning
image segmentation
policy evaluation
pattern recognition
average reward