Truncated Variance Reduced Value Iteration

Authors: Yujia Jin, Ishani Karmarkar, Aaron Sidford, Jiayi Wang

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical The paper focuses on theoretical results and mathematical analysis and does not include experiments.
Researcher Affiliation Academia Yujia Jin Stanford University yujiajin@stanford.edu Ishani Karmarkar Stanford University ishanik@stanford.edu Aaron Sidford Stanford University sdiford@stanford.edu Jiayi Wang Stanford University jyw@stanford.edu
Pseudocode Yes Algorithm 1: Sample(u, p, M, η) ... Algorithm 2: Apx Utility(u, M, η) ... Algorithm 3: TVRVI(v(0), π(0), x, α, δ) ... Algorithm 4: Offline TVRVI(ε, δ) ... Algorithm 5: Sample TVRVI(ε, δ) ... Algorithm 6: Problem Dependent TVRVI(ε, δ, V )
Open Source Code No The paper focuses on theoretical results and mathematical analysis and does not include experiments.
Open Datasets No The paper focuses on theoretical results and mathematical analysis and does not include experiments.
Dataset Splits No The paper focuses on theoretical results and mathematical analysis and does not include experiments.
Hardware Specification No The paper focuses on theoretical results and mathematical analysis and does not include experiments.
Software Dependencies No The paper focuses on theoretical results and mathematical analysis and does not include experiments.
Experiment Setup No The paper focuses on theoretical results and mathematical analysis and does not include experiments.