Learning a DFT-based sequence with reinforcement learning: a NAO implementation.

Boris Durán Gauss Lee Robert Lowe

Published in: Paladyn J. Behav. Robotics (2012)

Keyphrases

reinforcement learning
learning process
learning algorithm
learning problems
hidden state
online learning
prior knowledge
active learning
knowledge acquisition
optimal policy
frequency domain
background knowledge
temporal difference learning
evolutionary learning
eligibility traces