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..
On the Sample Complexity of Differentially Private Policy Optimization
Authors: Yi He, Xingyu Zhou
NeurIPS 2025 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | We conduct experiments on the Cart Pole-v1 environment from Open AI Gym, a standard benchmark for evaluating policy gradient methods. |
| Researcher Affiliation | Academia | Yi He Wayne State University EMAIL Xingyu Zhou Wayne State University EMAIL |
| Pseudocode | Yes | Algorithm 1 A Meta Algorithm |
| Open Source Code | No | 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: Our conclusions are derived through mathematical deduction and logical argumentation, so it does not include experiments requiring code. |
| Open Datasets | Yes | We conduct experiments on the Cart Pole-v1 environment from Open AI Gym, a standard benchmark for evaluating policy gradient methods. |
| Dataset Splits | No | The paper does not explicitly mention training/test/validation splits for a fixed dataset, which is typical for RL environments where data is generated through interaction. It mentions 'batch size 10 (i.e., 10 episodes per gradient update)' in Appendix H, but this refers to online data generation rather than static dataset splits. |
| Hardware Specification | No | The paper does not provide specific hardware details (e.g., GPU/CPU models, memory) used for running the experiments described in Appendix H. |
| Software Dependencies | No | The paper mentions 'Open AI Gym' in Appendix H but does not specify its version or any other software dependencies with version numbers. |
| Experiment Setup | Yes | All algorithms are trained for 100 epochs with batch size 10 (i.e., 10 episodes per gradient update) and discount factor γ = 0.99. We use advantage normalization with baseline subtraction for variance reduction. Each algorithm is trained with 3 random seeds, and we report the average performance with standard deviation. |