Federated Reinforcement Learning: Linear Speedup Under Markovian Sampling

Authors: Sajad Khodadadian, Pranay Sharma, Gauri Joshi, Siva Theja Maguluri

ICML 2022 | Conference PDF | Archive PDF | Plain Text | LLM Run Details

Reproducibility Variable Result LLM Response
Research Type Theoretical We propose federated versions of on-policy TD, off-policy TD and Q-learning, and analyze their convergence. For all these algorithms, to the best of our knowledge, we are the first to consider Markovian noise and multiple local updates, and prove a linear convergence speedup with respect to the number of agents.
Researcher Affiliation Academia 1H. Milton Stewart School of Industrial & Systems Engineering, Georgia Institute of Technology, Atlanta, GA, 30332, USA 2Electrical and Computer Engineering, Carnegie Mellon University, Pittsburgh, PA, 15213, USA
Pseudocode Yes Algorithm 1 Federated n-step TD (On-policy, Function Approx.), Algorithm 2 Federated n-step TD (Off-policy Tabular Setting), Algorithm 3 Federated Q-learning, Algorithm 4 Federated Stochastic Approximation with Markovian Noise (Fed SAM)
Open Source Code No The paper does not provide any statement or link regarding the availability of open-source code for the methodology described.
Open Datasets No The paper is theoretical and focuses on mathematical analysis and proofs, thus it does not use or specify any public or open datasets for training or evaluation.
Dataset Splits No This paper is purely theoretical and does not involve experimental validation with datasets, so no training/validation/test splits are specified.
Hardware Specification No This paper is theoretical and does not describe empirical experiments, therefore no specific hardware specifications for running experiments are provided.
Software Dependencies No This paper is theoretical and does not describe empirical experiments, therefore no specific software dependencies with version numbers are listed.
Experiment Setup No This paper is theoretical and focuses on mathematical analysis and proofs rather than empirical experiments, so it does not include details on experimental setup or hyperparameters.