Last-iterate Convergence in Extensive-Form Games

Authors: Chung-Wei Lee, Christian Kroer, Haipeng Luo

NeurIPS 2021 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Experimental We also provide experiments to further support our theoretical results.
Researcher Affiliation Academia Chung-Wei Lee University of Southern California leechung@usc.edu Christian Kroer Columbia University christian.kroer@columbia.edu Haipeng Luo University of Southern California haipengl@usc.edu
Pseudocode No The paper describes algorithms using mathematical equations and prose but does not provide structured pseudocode or algorithm blocks.
Open Source Code No The paper does not provide any statement or link indicating the release of open-source code for the described methodology.
Open Datasets Yes In this section, we experimentally evaluate the algorithms on three standard EFG benchmarks: Kuhn poker [Kuhn, 1950], Pursuit-evasion [Kroer et al., 2018], and Leduc poker [Southey et al., 2005].
Dataset Splits No The paper describes the game environments used for experiments but does not provide specific training/validation/test dataset splits or methodologies, as these are game simulations rather than typical static datasets with pre-defined splits.
Hardware Specification No The paper states: 'All the experiments are run on CPU in a personal computer' but does not provide specific details on the CPU model, memory, or other hardware components.
Software Dependencies No The paper does not list specific software dependencies with version numbers.
Experiment Setup Yes For each optimistic algorithm, we fine-tune step size η to get better convergence results and show its value in the legends.