• Mathematics
  • Published 2014

Stochastic approximation for efficient LSTD and least squares regression

@inproceedings{PrashanthL2014StochasticAF,
  title={Stochastic approximation for efficient LSTD and least squares regression},
  author={A. PrashanthL. and Nathaniel Korda and R{\'e}mi Munos},
  year={2014}
}
We propose stochastic approximation based methods with randomization of samples in two different settings - one for policy evaluation using the least squares temporal difference (LSTD) algorithm and the other for solving the least squares problem. We consider a “big data” regime where both the dimension, d, of the data and the number, T, of training samples are large. Through finite time analyses we provide performance bounds for these methods both in high probability and in expectation. In… CONTINUE READING
1
Twitter Mention

References

Publications referenced by this paper.
SHOWING 1-10 OF 22 REFERENCES

Least-Squares Policy Iteration

VIEW 6 EXCERPTS
HIGHLY INFLUENTIAL

Approximate Dynamic Programming

VIEW 2 EXCERPTS
HIGHLY INFLUENTIAL

Finite-sample analysis of least-squares policy iteration

VIEW 2 EXCERPTS

Icml exploration and exploitation 3 - new challenges

  • J. Mary, Aurlien Garivier, +4 authors P. Preux
  • 2012

Threshold Tuning Using Stochastic Optimization for Graded Signal Control

VIEW 1 EXCERPT