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..
Converging to Team-Maxmin Equilibria in Zero-Sum Multiplayer Games
Authors: Youzhi Zhang, Bo An
ICML 2020 | Venue PDF | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Experimental | Finally, extensive experimental results show that CISGT is orders of magnitude faster than ISGT and the state-of-the-art algorithm to compute TMEs in large games. |
| Researcher Affiliation | Academia | 1School of Computer Science and Engineering, Nanyang Technological University, Singapore. |
| Pseudocode | Yes | Algorithm 1 ISG for a TME (ISGT) and Algorithm 2 The CTME Based ISGT (CISGT) |
| Open Source Code | No | The paper does not provide an explicit statement or link for the open-source code of the described methodology. |
| Open Datasets | Yes | We conduct experiments on the classic network security games (Washburn & Wood, 1995; Jain et al., 2011; Iwashita et al., 2016)... All networks are generated by the grid model with random edges (Peng et al., 2014)... |
| Dataset Splits | No | The paper mentions generating random instances for experiments but does not explicitly detail training, validation, or test dataset splits (e.g., percentages, sample counts, or predefined splits). |
| Hardware Specification | Yes | All experiments are run on a machine with 6-core 3.6GHz CPU and 32GB memory. |
| Software Dependencies | Yes | We use CPLEX solver (version 12.9) for solving all linear programs. |
| Experiment Setup | Yes | We conduct experiments on the classic network security games... (i.e., ϵ-TME with ϵ = 0.05)... By default, n = 3, and results are all averaged over 30 instances that are randomly generated. |