Cooperative Multi-Agent Reinforcement Learning: Asynchronous Communication and Linear Function Approximation

Authors: Yifei Min, Jiafan He, Tianhao Wang, Quanquan Gu

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

Reproducibility Variable Result LLM Response
Research Type Theoretical We propose a provably efficient algorithm based on value iteration that enable asynchronous communication while ensuring the advantage of cooperation with low communication overhead. With linear function approximation, we prove that our algorithm enjoys an e O(d3/2H2 K) regret with e O(d HM 2) communication complexity... We also provide a lower bound showing that a minimal Ω(d M) communication complexity is required to improve the performance through collaboration.
Researcher Affiliation Academia Yifei Min * 1 Jiafan He * 2 Tianhao Wang * 1 Quanquan Gu 2 1Department of Statistics and Data Science, Yale University 2Department of Computer Science, University of California, Los Angeles. Correspondence to: Quanquan Gu <qgu@cs.ucla.edu>.
Pseudocode Yes Algorithm 1 Communication Protocol
Open Source Code No The paper does not provide an explicit statement about releasing open-source code or a link to a code repository for the described methodology.
Open Datasets No The paper is theoretical and focuses on algorithmic design and theoretical analysis; therefore, it does not mention specific datasets used for training or their public availability.
Dataset Splits No The paper is theoretical and does not describe experimental validation; therefore, it does not provide dataset splits for training, validation, or testing.
Hardware Specification No The paper does not specify any particular hardware used for its research or theoretical derivations.
Software Dependencies No The paper does not mention any specific software dependencies with version numbers.
Experiment Setup No The paper is theoretical and does not include details about an experimental setup, such as hyperparameters or system-level training settings.