Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning

Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
Peter L. Bartlett and Evan Greensmith and Jonathan Baxter

Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning.pdf	324.36kB

Type: Paper
Tags:

Bibtex:

@article{5:54,author={Evan Greensmith and Peter L. Bartlett and Jonathan Baxter}, Title={Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning},journal={Journal of Machine Learning Research},volume={5}, url={http://www.jmlr.org/papers/volume5/hoyer04a/hoyer04a.pdf}}

Send Feedback

Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning Peter L. Bartlett and Evan Greensmith and Jonathan Baxter

Variance Reduction Techniques for Gradient Estimates in Reinforcement Learning
Peter L. Bartlett and Evan Greensmith and Jonathan Baxter