Efficient Sample Reuse in EM-Based Policy Search

Hirotaka Hachiya, Jan Peters, Masashi Sugiyama

Abstract

Direct policy search is a promising reinforcement learning framework in particular for controlling in continuous, high-dimensional systems such as anthropomorphic robots. Policy search often requires a large number of samples for obtaining a stable policy update estimator due to its high flexibility. However, this is prohibitive when the sampling cost is expensive. In this paper, we extend an EM-based policy search method so that previously collected samples can be efficiently reused. The usefulness of the proposed method, called Reward-weighted Regression with sample Reuse (R3), is demonstrated through a robot learning experiment.
BibTeX
@inproceedings{hachiya2009efficient,
  author = {Hirotaka Hachiya and Jan Peters and Masashi Sugiyama},
  title = {{Efficient Sample Reuse in EM-Based Policy Search}},
  booktitle = {ECML/PKDD},
  year = {2009},
  doi = {10.1007/978-3-642-04180-8\_48},
}

Loading related content...

Figure