Improving Spatiotemporal Self-supervision by Deep Reinforcement Learning.

Uta Büchler Biagio Brattoli Björn Ommer

Published in: ECCV (15) (2018)

Keyphrases

reinforcement learning
function approximation
spatial and temporal
machine learning
learning algorithm
active learning
data mining
search algorithm
state space
space time
model free
decision trees
multi agent
dynamic programming
optimal policy
action selection