Learning While Playing in Mean-Field Games: Convergence and Optimality

Authors: Qiaomin Xie, Zhuoran Yang, Zhaoran Wang, Andreea Minca

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

Reproducibility Variable Result LLM Response
Research Type Theoretical To bridge such a gap, we propose a fictitious play algorithm, which alternatively updates the policy (learning) and the mean-field state (playing) by one step of policy optimization and gradient descent, respectively. Despite the nonstationarity induced by such an alternating scheme, we prove that the proposed algorithm converges to the Nash equilibrium with an explicit convergence rate. To the best of our knowledge, it is the first provably efficient algorithm that achieves learning while playing.
Researcher Affiliation Academia 1School of Operations Research and Information Engineering, Cornell University 2Department of Operations Research and Financial Engineering, Princeton University 3Department of Industrial Engineering and Management Sciences, Northwestern University.
Pseudocode Yes Algorithm 1 Mean-Embedded Fictitious Play
Open Source Code No The paper does not provide any statement about making its source code available or a link to a code repository.
Open Datasets No The paper is theoretical and focuses on algorithm design and convergence proofs; it does not utilize or describe any datasets for empirical training or evaluation.
Dataset Splits No The paper is theoretical and does not involve empirical data splits for training, validation, or testing.
Hardware Specification No The paper is theoretical and does not describe any hardware used for experiments.
Software Dependencies No The paper is theoretical and does not list any specific software dependencies with version numbers for experimental reproducibility.
Experiment Setup No The paper is theoretical and does not describe an experimental setup, hyperparameters, or training configurations.