Learning Equilibria of Games via Payoff Queries
Authors: John Fearnley, Martin Gairing, Paul W. Goldberg, Rahul Savani
JMLR 2015 | Venue PDF | Archive PDF | Plain Text | LLM Run Details
| Reproducibility Variable | Result | LLM Response |
|---|---|---|
| Research Type | Theoretical | We study a corresponding computational learning model, and the query complexity of learning equilibria for various classes of games. We give basic results for exact equilibria of bimatrix and graphical games. We then study the query complexity of approximate equilibria in bimatrix games. Finally, we study the query complexity of exact equilibria in symmetric network congestion games. |
| Researcher Affiliation | Academia | John Fearnley EMAIL Martin Gairing EMAIL Ashton Building, Ashton Street, University of Liverpool, United Kingdom Paul W. Goldberg EMAIL Wolfson Building, Parks Road, University of Oxford, United Kingdom Rahul Savani EMAIL Ashton Building, Ashton Street, University of Liverpool, United Kingdom |
| Pseudocode | Yes | Algorithm 1 Graphical Games |
| Open Source Code | No | The paper does not provide any explicit statements about releasing source code, nor does it include links to a code repository. |
| Open Datasets | No | The paper is theoretical and focuses on query complexity; it does not present experimental results based on specific datasets provided by the authors. Mentions of 'data sets' in the introduction and related work refer to general contexts or other studies. |
| Dataset Splits | No | The paper does not present experimental results using datasets, thus there is no information on dataset splits. |
| Hardware Specification | No | The paper focuses on theoretical aspects and does not describe any experiments that would require specific hardware specifications. |
| Software Dependencies | No | The paper is theoretical and does not describe implementation details or mention specific software dependencies with version numbers. |
| Experiment Setup | No | The paper primarily presents theoretical results, including algorithms, proofs, and complexity analysis. It does not describe an experimental setup with specific hyperparameters or training configurations for empirical evaluation. |