Adaptive Step-Size for Online Temporal Difference Learning

  title={Adaptive Step-Size for Online Temporal Difference Learning},
  author={William Dabney and Andrew G. Barto},
The step-size, often denoted as α, is a key parameter for most incremental learning algorithms. Its importance is especially pronounced when performing online temporal difference (TD) learning with function approximation. Several methods have been developed to adapt the step-size online. These range from straightforward back-off strategies to adaptive algorithms based on gradient descent. We derive an adaptive upper bound on the step-size parameter to guarantee that online TD learning with… CONTINUE READING
Highly Cited
This paper has 48 citations. REVIEW CITATIONS


Publications citing this paper.
Showing 1-10 of 25 extracted citations

Similar Papers

Loading similar papers…