The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond Article Swipe

MAKE IMPACT

Jiin Woo , Gauri Joshi , Yuejie Chi · YOU? · · 2023 · Open Access · · DOI: https://doi.org/10.48550/arxiv.2305.10697

When the data used for reinforcement learning (RL) are collected by multiple agents in a distributed manner, federated versions of RL algorithms allow collaborative learning without the need for agents to share their local data. In this paper, we consider federated Q-learning, which aims to learn an optimal Q-function by periodically aggregating local Q-estimates trained on local data alone. Focusing on infinite-horizon tabular Markov decision processes, we provide sample complexity guarantees for both the synchronous and asynchronous variants of federated Q-learning. In both cases, our bounds exhibit a linear speedup with respect to the number of agents and near-optimal dependencies on other salient problem parameters. In the asynchronous setting, existing analyses of federated Q-learning, which adopt an equally weighted averaging of local Q-estimates, require that every agent covers the entire state-action space. In contrast, our improved sample complexity scales inverse proportionally to the minimum entry of the average stationary state-action occupancy distribution of all agents, thus only requiring the agents to collectively cover the entire state-action space, unveiling the blessing of heterogeneity in enabling collaborative learning by relaxing the coverage requirement of the single-agent case. However, its sample complexity still suffers when the local trajectories are highly heterogeneous. In response, we propose a novel federated Q-learning algorithm with importance averaging, giving larger weights to more frequently visited state-action pairs, which achieves a robust linear speedup as if all trajectories are centrally processed, regardless of the heterogeneity of local behavior policies.

Type

preprint

Language

en

Landing Page

http://arxiv.org/abs/2305.10697

PDF

https://arxiv.org/pdf/2305.10697

OA Status

green

Cited By

4

Related Works

10

OpenAlex ID

https://openalex.org/W4377130806

Raw OpenAlex JSON

OpenAlex ID

https://openalex.org/W4377130806

Canonical identifier for this work in OpenAlex

DOI

https://doi.org/10.48550/arxiv.2305.10697

Digital Object Identifier

Title

The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond

Work title

Type

preprint

OpenAlex work type

Language

en

Primary language

Publication year

2023

Year of publication

Publication date

2023-05-18

Full publication date if available

Authors

Jiin Woo, Gauri Joshi, Yuejie Chi

List of authors in order

Landing page

https://arxiv.org/abs/2305.10697

Publisher landing page

PDF URL

https://arxiv.org/pdf/2305.10697

Direct link to full text PDF

Open access

Yes

Whether a free full text is available

OA status

green

Open access status per OpenAlex

OA URL

https://arxiv.org/pdf/2305.10697

Direct OA link when available

Concepts

Speedup, Computer science, Asynchronous communication, Reinforcement learning, Markov decision process, Sample (material), State space, Action (physics), State (computer science), Artificial intelligence, Algorithm, Markov process, Mathematics, Parallel computing, Quantum mechanics, Computer network, Chemistry, Chromatography, Statistics, Physics

Top concepts (fields/topics) attached by OpenAlex

Cited by

4

Total citation count in OpenAlex

Citations by year (recent)

2025: 2, 2024: 2

Per-year citation counts (last 5 years)

Related works (count)

10

Other works algorithmically related by OpenAlex

Full payload