Regret Matching+: (In)Stability and Fast Convergence in Games

Authors: Gabriele Farina, Julien Grand-Clément, Christian Kroer, Chung-Wei Lee, Haipeng Luo

NeurIPS 2023 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental Our experiments show the advantages of our algorithms over vanilla RM+-based algorithms in matrix and extensive-form games.
Researcher Affiliation Academia Gabriele Farina MIT gfarina@mit.edu Julien Grand-Cl ement ISOM, HEC Paris grand-clement@hec.fr Christian Kroer IEOR, Columbia University christian.kroer@columbia.edu Chung-Wei Lee Department of Computer Science University of Southern California leechung@usc.edu Haipeng Luo Department of Computer Science University of Southern California haipengl@usc.edu
Pseudocode Yes Algorithm 1 Stable Predictive RM+; Algorithm 2 Smooth Predictive RM+; Algorithm 3 Conceptual RM+; Algorithm 4 Conceptual RM+ with approximate fixed-point; Algorithm 5 Extragradient RM+
Open Source Code No The paper does not provide any concrete access information (e.g., a specific repository link, explicit code release statement, or code in supplementary materials) for the methodology described.
Open Datasets Yes We compute the performance of Ex RM+, Stable and Smooth PRM+ on the 3 3 matrix game instance from Section 2 ... Our experiments on 4 different EFGs show that our implementation of clairvoyant CFR outperforms predictive CFR in some, but not all, instances. We used the following games in the experiments: 2-player Sheriff (Farina et al. [11]), 3-player Leduc poker ([33]), 4-player Kuhn poker ([26]), 4-player Liar s dice ([27]).
Dataset Splits No The paper mentions the use of specific games and matrix instances but does not provide details on training, validation, or test dataset splits (e.g., percentages, sample counts, or references to predefined splits).
Hardware Specification No The paper does not specify any hardware details (e.g., GPU models, CPU models, or cloud computing instance types) used for running its experiments.
Software Dependencies No The paper does not provide specific ancillary software details, such as library names with version numbers (e.g., Python 3.8, PyTorch 1.9, CPLEX 12.4), needed to replicate the experiment.
Experiment Setup Yes We compute the performance of Ex RM+, Stable and Smooth PRM+ on the 3 3 matrix game instance from Section 2 (with step size η = 0.1) and on 30 random matrix games of size (d1, d2) = (30, 40) with normally distributed coefficients of the payoff matrix and with step sizes η {0.1, 1, 10}. We initialize our algorithms at (1/d1)1d, all algorithms use linear averaging, and all algorithms (except Ex RM+) use alternation.