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..
Computational Hardness of Reinforcement Learning with Partial $q^{\pi}$-Realizability
Authors: Shayan Karimi, Xiaoqi Tan
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | This paper is purely theoretical and does not include any experimental results. The main contributions consist of formal definitions, complexity-theoretic results, and complete proofs, all of which are fully disclosed in the paper and appendix. |
| Researcher Affiliation | Academia | Shayan Karimi University of Alberta Edmonton, Canada EMAIL Xiaoqi Tan University of Alberta Edmonton, Canada EMAIL |
| Pseudocode | No | The paper describes algorithms conceptually (e.g., "We aim to design an ASAT algorithm"), but does not contain any explicitly structured pseudocode blocks or algorithms labeled as such. The algorithmic steps are described in prose within the proofs and problem statements. |
| Open Source Code | No | This paper is purely theoretical and does not include any experiments, datasets, or code. The contributions consist of complexity-theoretic results and formal proofs, all of which are fully described in the main text and appendix. |
| Open Datasets | No | This paper is purely theoretical and does not include any experiments, datasets, or code. The contributions consist of complexity-theoretic results and formal proofs, all of which are fully described in the main text and appendix. |
| Dataset Splits | No | This is a theoretical paper with no experimental setup, and thus no datasets or dataset splits are discussed. |
| Hardware Specification | No | This work is purely theoretical and does not include any experiments or computational benchmarks requiring resource specification. |
| Software Dependencies | No | This is a theoretical paper with no experimental setup, and thus no specific software dependencies are mentioned. |
| Experiment Setup | No | This is a theoretical paper with no experimental setup. The contributions are formal complexity results and proofs, which are fully detailed in the main text and appendix. |