Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem

Authors: Fivos Kalogiannis, Jingming Yan, Ioannis Panageas

NeurIPS 2024 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical Question: Does the paper conduct EMPIRICAL STUDIES WITH DATA ANALYSIS (experiments, dataset evaluation, performance metrics, or hypothesis validation) rather than purely theoretical work? Answer: [No] Justification: The paper is theoretical in nature and does not include experiments.
Researcher Affiliation Academia Fivos Kalogiannis University of California, Irvine Archimedes/Athena RC, Greece Jingming Yan University of California, Irvine Ioannis Panageas University of California, Irvine Archimedes/Athena RC, Greece
Pseudocode Yes Algorithm 1 Independent Stochastic Policy-Nested-Gradient (ISPNG) Algorithm 2 Visitation-Regularized Policy Gradient Algorithm (VIS-REG-PG)
Open Source Code No The paper does not include experiments requiring code.
Open Datasets No The paper does not include experiments, so it does not discuss training datasets or their public availability.
Dataset Splits No The paper does not include experiments, so it does not discuss training, validation, or test dataset splits.
Hardware Specification No The paper does not include experiments, so no hardware specifications are mentioned.
Software Dependencies No The paper does not include experiments, so no specific software dependencies with version numbers are listed.
Experiment Setup No The paper does not include experiments, so it does not detail specific experimental setup, hyperparameters, or training configurations.