Toward Provably Unbiased Temporal-Difference Value Estimation Roy Fox Optimization Foundations for Reinforcement Learning workshop (OPTRL @ NeurIPS), 2019 BibTeX × @conference{ Fox2019Toward, Title = "Toward Provably Unbiased Temporal-Difference Value Estimation", Author = "Roy Fox", Booktitle = "Optimization Foundations for Reinforcement Learning workshop (OPTRL @ NeurIPS)", Year = "2019" }