Incremental Least-Squares Temporal Difference Learning

  title={Incremental Least-Squares Temporal Difference Learning},
  author={Alborz Geramifard and Michael H. Bowling and Richard S. Sutton},
Approximate policy evaluation with linear function approximation is a commonly arising problem in reinforcement learning, usually solved using temporal difference (TD) algorithms. In this paper we introduce a new variant of linear TD learning, called incremental least-squares TD learning, or iLSTD. This method is more data efficient than conventional TD algorithms such as TD(0) and is more computationally efficient than non-incremental least-squares TD methods such as LSTD (Bradtke & Barto 1996… CONTINUE READING
Highly Cited
This paper has 93 citations. REVIEW CITATIONS


Publications citing this paper.

94 Citations

Citations per Year
Semantic Scholar estimates that this publication has 94 citations based on the available data.

See our FAQ for additional information.