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..
Thresholds for sensitive optimality and Blackwell optimality in stochastic games
Authors: Stephane Gaubert, Julien Grand-Clément, Ricardo Katz
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We investigate refinements of the mean-payoff criterion in two-player zero-sum perfect-information stochastic games. [...] We provide the first bounds on the d-sensitive threshold αd beyond the case d = 1, and we establish improved bounds for the Blackwell threshold αBw. This is achieved by leveraging separation bounds on algebraic numbers, relying on Lagrange bounds and more advanced techniques based on Mahler measures and multiplicity theorems. [...] There are no numerical experiments in this paper. |
| Researcher Affiliation | Academia | Stéphane Gaubert INRIA and Ecole Polytechnique EMAIL Julien Grand-Clément HEC Paris EMAIL Ricardo D. Katz CIFASIS-CONICET EMAIL |
| Pseudocode | No | The paper describes theoretical results and mathematical proofs. There are no figures, blocks, or sections labeled 'Pseudocode' or 'Algorithm'. |
| Open Source Code | No | Answer: [NA] Justification: There are no numerical experiments in this paper. [...] Question: Does the paper provide open access to the data and code, with sufficient instructions to faithfully reproduce the main experimental results, as described in supplemental material? Answer: [NA] Justification: There are no numerical experiments in this paper. |
| Open Datasets | No | Answer: [NA] Justification: There are no numerical experiments in this paper. [...] Question: Does the paper provide open access to the data and code, with sufficient instructions to faithfully reproduce the main experimental results, as described in supplemental material? Answer: [NA] Justification: There are no numerical experiments in this paper. |
| Dataset Splits | No | Answer: [NA] Justification: There are no numerical experiments in this paper. The paper focuses on theoretical analysis and mathematical bounds for stochastic games, not on experiments using datasets. |
| Hardware Specification | No | Answer: [NA] Justification: There are no numerical experiments in this paper. The paper focuses on theoretical analysis and mathematical proofs, not on empirical studies requiring specific hardware. |
| Software Dependencies | No | Answer: [NA] Justification: There are no numerical experiments in this paper. The paper focuses on theoretical analysis and mathematical proofs, not on empirical studies requiring specific software versions. |
| Experiment Setup | No | Answer: [NA] Justification: There are no numerical experiments in this paper. The paper is entirely theoretical, focusing on mathematical bounds and proofs rather than experimental setups or hyperparameters. |