@article{softtreemaxexponentialvariancereductioni,
  title = {SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search},
  author = {Gal Dalal and Assaf Hallak and Gugan Thoppe and Shie Mannor and Gal Chechik},
  year = {2023},
  eprint = {2301.13236},
  archivePrefix = {arXiv},
  url = {https://arxiv.org/abs/2301.13236v1},
}