Loading Now

Summary of Federated Q-learning with Reference-advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost, by Zhong Zheng et al.


Federated Q-Learning with Reference-Advantage Decomposition: Almost Optimal Regret and Logarithmic Communication Cost

by Zhong Zheng, Haochen Zhang, Lingzhou Xue

First submitted to arxiv on: 29 May 2024

Categories

  • Main: Machine Learning (stat.ML)
  • Secondary: Machine Learning (cs.LG)

     Abstract of paper      PDF of paper


GrooveSquid.com Paper Summaries

GrooveSquid.com’s goal is to make artificial intelligence research accessible by summarizing AI papers in simpler terms. Each summary below covers the same AI paper, written at different levels of difficulty. The medium difficulty and low difficulty versions are original summaries written by GrooveSquid.com, while the high difficulty version is the paper’s original abstract. Feel free to learn from the version that suits you best!

Summary difficulty Written by Summary
High Paper authors High Difficulty Summary
Read the original abstract here
Medium GrooveSquid.com (original content) Medium Difficulty Summary
A novel model-free federated reinforcement learning algorithm is proposed for tabular episodic Markov decision processes. The algorithm, called FedQ-Advantage, enables multiple agents to collaboratively explore an environment and learn an optimal policy without sharing their raw data. This is achieved through reference-advantage decomposition for variance reduction and two distinct mechanisms: synchronization between agents and a central server, and policy update, both triggered by events. The proposed algorithm requires lower logarithmic communication cost and achieves almost optimal regret, reaching the information bound up to a logarithmic factor and near-linear regret speedup compared to its single-agent counterpart when the time horizon is sufficiently large.
Low GrooveSquid.com (original content) Low Difficulty Summary
In this paper, scientists explore a new way for computers to learn together without sharing all their data. This helps them find the best way to solve problems in complex situations. The algorithm they created, FedQ-Advantage, makes it possible for multiple computers to work together and learn from each other without sharing everything. This is important because it could be used in many areas like medicine or finance where data needs to be protected.

Keywords

» Artificial intelligence  » Reinforcement learning