Discovering and Exploiting Sparse Rewards in a Learned Behavior Space.

Giuseppe Paolo Alexandre Coninx Alban Laflaquière Stéphane Doncieux

Published in: CoRR (2021)

Keyphrases

markov decision processes
reinforcement learning
neural network
sparse data
sparse representation
search space
website
search algorithm
high dimensional
information systems
low dimensional
computer vision
social networks
sparse coding
planning problems
dictionary learning
data sets
bandit problems