Follow
Near-Optimal Offline Reinforcement Learning via Double Variance Reduction. (arXiv:2102.01748v1 [cs.LG]) http://arxiv.org/abs/2102.01748
Near-Optimal Offline Reinforcement Learning via Double Variance Reduction. (arXiv:2102.01748v1 [cs.LG]) http://arxiv.org/abs/2102.01748