Follow
SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search. (arXiv:2301.13236v1 [cs.LG]) http://arxiv.org/abs/2301.13236
SoftTreeMax: Exponential Variance Reduction in Policy Gradient via Tree Search. (arXiv:2301.13236v1 [cs.LG]) http://arxiv.org/abs/2301.13236