Follow
Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration. (arXiv:2202.00076v1 [stat.ML]) http://arxiv.org/abs/2202.00076
Optimal Estimation of Off-Policy Policy Gradient via Double Fitted Iteration. (arXiv:2202.00076v1 [stat.ML]) http://arxiv.org/abs/2202.00076