Notice: This website is continuously updated as new conference proceedings and journal volumes are published. Consequently, the figures presented here may differ from those reported in our publications.
A brief overview of our methodology is provided on the Methods page, along with references to publications documenting our approach and links to the code and data used in each study.
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.
Decentralised Learning in Systems With Many, Many Strategic Agents
Authors: David Mguni, Joel Jennings, Enrique Munoz de Cote
AAAI 2018 | Venue PDF | LLM Run Details | Input Tokens: 16,166 Total number of tokens sent to the LLM as input for this paper's analysis. | Output Tokens: 3,932 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 | We validate these theoretical results by showing convergence to Nash-equilibrium policies in applications from economics and control theory with thousands of strategically interacting agents. Experiment 1: Spatial Congestion Game. Experiment 2: Supply with Uncertain Demand. Experiment 3: Mean-Field Linear Quadratic Regulator. |
| Researcher Affiliation | Collaboration | 1PROWLER.io, Cambridge, UK 2Department of Computer Science, INAOE, Mexico |
| Pseudocode | No | The paper describes the learning procedure but does not include any pseudocode or algorithm blocks. |
| Open Source Code | No | The paper does not provide any statement or link indicating the availability of open-source code for the described methodology. |
| Open Datasets | No | The paper describes experiment setups based on benchmark *problem types* but does not specify using or providing access to any publicly available *datasets* in the traditional sense. For example, for the Spatial Congestion Game, it defines reward functions and transition dynamics with parameters, rather than referencing a specific dataset file. |
| Dataset Splits | No | The paper does not specify explicit dataset splits (e.g., percentages or counts) for training, validation, or testing data. It mentions |
| Hardware Specification | No | The paper does not explicitly describe the specific hardware used for running the experiments. |
| Software Dependencies | No | The paper does not provide specific version numbers for any software dependencies. |
| Experiment Setup | Yes | Experiment 1: Spatial Congestion Game: α {1.0, 2.0, 3.0}, μ R2, Σ 12 2, R = η1(2 2), σ1, A1, B1 1(2 2) and c, σϵ R+. Experiment 2: Supply with Uncertain Demand: fixed number (30) time steps. Experiment 3: Mean-Field Linear Quadratic Regulator: C(xt, mxt) (xt α)T Qt(xt α), ut R2 1, A1, B1 1(2 2), σ1 = c1(2 2). |