Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning.

Evan Greensmith Peter L. Bartlett Jonathan Baxter Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning. 1471-1530 2004 5 Journal of Machine Learning Research http://www.jmlr.org/papers/volume5/greensmith04a/greensmith04a.pdf db/journals/jmlr/jmlr5.html#GreensmithBB04