Jervis Pinto, Alan Fern, Tim Bauer, Martin Erwig. Improving Policy Gradient Estimates with Influence Information. Journal of Machine Learning Research, 20:1-18, 2011. [doi]
@article{PintoFBE11, title = {Improving Policy Gradient Estimates with Influence Information}, author = {Jervis Pinto and Alan Fern and Tim Bauer and Martin Erwig}, year = {2011}, url = {http://www.jmlr.org/proceedings/papers/v20/pinto11/pinto11.pdf}, researchr = {https://researchr.org/publication/PintoFBE11}, cites = {0}, citedby = {0}, journal = {Journal of Machine Learning Research}, volume = {20}, pages = {1-18}, }