Login / Signup
Safe Policy Improvement with Baseline Bootstrapping.
Romain Laroche
Paul Trichelair
Remi Tachet des Combes
Published in:
ICML (2019)
Keyphrases
</>
error reduction
data sets
video sequences
optimal policy
significant improvement
named entity recognition
policy making
database
information systems
decision making
decision trees
weakly supervised
asymptotically optimal
policy search