Policy Learning with Hypothesis based Local Action Selection.

Bharath Sankaran Jeannette Bohg Nathan D. Ratliff Stefan Schaal

Published in: CoRR (2015)

Keyphrases

action selection
reinforcement learning
learning process
basal ganglia
temporal difference
robot soccer
learning algorithm
decision making
learning tasks
active learning
online learning
markov chain
human robot
inverse reinforcement learning