Notice: The reproducibility variables underlying each score are classified using an automated LLM-based pipeline, validated against a manually labeled dataset. LLM-based classification introduces uncertainty and potential bias; scores should be interpreted as estimates. Full accuracy metrics and methodology are described in Coakley et alK. L. Coakley, T. Snelleman, H. Hoos, and O. E. Gundersen, "The embrace of open science: An analysis of a decade of AI research and 56 800 conference papers," Under Review, 2026..

A Finite Sample Analysis of Distributional TD Learning with Linear Function Approximation

Authors: Yang Peng, Kaicheng Jin, Liangyu Zhang, Zhihua Zhang

NeurIPS 2025 | Venue PDF | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our numerical experiments have provided empirical validation of our theoretical results.
Researcher Affiliation Academia School of Mathematical Sciences, Peking University; email: EMAIL. School of Mathematical Sciences, Peking University; email: EMAIL. School of Statistics and Data Science, Shanghai University of Finance and Economics; email: EMAIL. School of Mathematical Sciences, School of Computer Science, Peking University; Center for Intelligent Computing, Great Bay University; email: EMAIL.
Pseudocode No The paper describes algorithms (Linear-TD and Linear-CTD) using mathematical update equations (e.g., Eqn. (5) and Eqn. (13)), but it does not present them in a clearly labeled or structured pseudocode block.
Open Source Code Yes We provide the code in supplemental material.
Open Datasets No The numerical experiments in Appendix G describe a simulated 3-state MDP environment and feature matrix, rather than using or providing access to a publicly available dataset. No specific dataset links, DOIs, or citations to well-known public datasets are provided.
Dataset Splits No The numerical experiments describe a simulated 3-state MDP and do not involve explicit dataset splits like training, validation, or test sets.
Hardware Specification Yes All of the experiments are conducted on a server with 4 NVIDIA RTX 4090 GPUs and Intel(R) Xeon(R) Gold 6132 CPU @ 2.60GHz.
Software Dependencies No The paper mentions providing code in supplementary material but does not explicitly list specific software dependencies with their version numbers (e.g., Python 3.x, PyTorch 1.x).
Experiment Setup Yes All of the experiments share zero initialization θ0 = 0 with max iteration=500000 and batch size=25.