R. S. Sutton and A. G. Barto, “Rein-forcement Learning: An introduction”, The MIT Press, Cambridge, 1998.

has been cited by the following article:

• TITLE: Multiple Action Sequence Learning and Automatic Generation for a Humanoid Robot Using RNNPB and Reinforcement Learning

  AUTHORS: Takashi Kuremoto, Koichi Hashiguchi, Keita Morisaki, Shun Watanabe, Kunikazu Kobayashi, Shingo Mabu, Masanao Obayashi

  KEYWORDS: RNNPB; Humanoid robot; BPTT; reinforcement learning; multiple action sequences

  JOURNAL NAME: Journal of Software Engineering and Applications, Vol.5 No.12B, January 25, 2013

  ABSTRACT: This paper proposes how to learn and generate multiple action sequences of a humanoid robot. At first, all the basic action sequences, also called primitive behaviors, are learned by a recurrent neural network with parametric bias (RNNPB) and the value of the internal nodes which are parametric bias (PB) determining the output with different primitive behaviors are obtained. The training of the RNN uses back propagation through time (BPTT) method. After that, to generate the learned behaviors, or a more complex behavior which is the combination of the primitive behaviors, a reinforcement learning algorithm: Q-learning (QL) is adopt to determine which PB value is adaptive for the generation. Finally, using a real humanoid robot, the proposed method was confirmed its effectiveness by the results of experiment.