%0 Journal Article %1 journals/corr/abs-2301-13236 %A Dalal, Gal %A Hallak, Assaf %A Thoppe, Gugan %A Mannor, Shie %A Chechik, Gal %D 2023 %J CoRR %K dblp %T SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search. %U http://dblp.uni-trier.de/db/journals/corr/corr2301.html#abs-2301-13236 %V abs/2301.13236

@article{journals/corr/abs-2301-13236, added-at = {2023-02-02T00:00:00.000+0100}, author = {Dalal, Gal and Hallak, Assaf and Thoppe, Gugan and Mannor, Shie and Chechik, Gal}, biburl = {https://www.bibsonomy.org/bibtex/2e88b20592f0a4af7f4f0b0e0d52f6607/dblp}, ee = {https://doi.org/10.48550/arXiv.2301.13236}, interhash = {5970b66f728dff92f284157eb0271cba}, intrahash = {e88b20592f0a4af7f4f0b0e0d52f6607}, journal = {CoRR}, keywords = {dblp}, timestamp = {2024-04-08T23:03:02.000+0200}, title = {SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search.}, url = {http://dblp.uni-trier.de/db/journals/corr/corr2301.html#abs-2301-13236}, volume = {abs/2301.13236}, year = 2023 }