Polynomial-Time Optimal Equilibria with a Mediator in Extensive-Form Games

Authors: Brian Zhang, Tuomas Sandholm

NeurIPS 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We back up our theoretical claims with experiments on a suite of standard benchmark games. ... We ran our algorithm for communication and full-certification equilibria on various two-player games, and compared the results to those given by notions of optimal correlation in games.
Researcher Affiliation Collaboration Brian Hu Zhang Computer Science Department Carnegie Mellon University bhzhang@cs.cmu.edu Tuomas Sandholm Computer Science Department, CMU Strategic Machine, Inc. Strategy Robot, Inc. Optimized Markets, Inc. sandholm@cs.cmu.edu
Pseudocode No The paper describes the construction of the mediator-augmented game and refers to solving a linear program but does not provide pseudocode or an algorithm block.
Open Source Code No Did you include the code, data, and instructions needed to reproduce the main experimental results (either in the supplemental material or as a URL)? [No]
Open Datasets Yes We ran our algorithm for communication and full-certification equilibria on various two-player games... The games used in the experiments are given in Appendix D. All experiments were allocated four CPU cores and 64 GB of RAM.
Dataset Splits No The paper does not specify any training, validation, or test dataset splits.
Hardware Specification Yes All experiments were allocated four CPU cores and 64 GB of RAM.
Software Dependencies Yes Linear programs were solved with Gurobi 9.5.
Experiment Setup Yes When payments are used, the allowable payment range is [0, M] where M is the reward range of the game.