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 Shift Toward Open and Reproducible AI Research," Under Review, 2026. doi: 10.48550/arXiv.2606.16974..
The Mechanics of n-Player Differentiable Games
Authors: David Balduzzi, Sebastien Racaniere, James Martens, Jakob Foerster, Karl Tuyls, Thore Graepel
ICML 2018 | Venue PDF | LLM Run Details | Input Tokens: 16,298 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 5,899 Total number of tokens produced by the LLM (including reasoning/thinking tokens) for this paper's analysis.
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Section 4 investigates a basic GAN setup from Metz et al. (2017)... Basic experiments show SGA is competitive with recently proposed algorithms for ๏ฌnding stable ๏ฌxed points in GANs whilst at the same time being applicable to and having guarantees in much more general games. |
| Researcher Affiliation | Collaboration | 1Deep Mind 2University of Oxford. Correspondence to: David Balduzzi <EMAIL>. |
| Pseudocode | Yes | Algorithm 1 Symplectic Gradient Adjustment |
| Open Source Code | Yes | Appendix C contains Tensor Flow code to compute the adjustment. |
| Open Datasets | No | No |
| Dataset Splits | No | No |
| Hardware Specification | No | No |
| Software Dependencies | No | No |
| Experiment Setup | Yes | The generator and discriminator networks both have 6 Re LU layers of 384 neurons. The generator has two output neurons; the discriminator has one. The networks are trained under RMSProp. Learning rates were chosen by visual inspection of grid search results at iteration 8000, see appendix. |