SOURCE-LINKED INTELLIGENCE

Provably Efficient Federated Reinforcement Learning with Linear Function Approximation and Logarithmic Communication Cost

arXiv · AI, language, vision and robotics · article · Aug 31, 2026 · UTC

We study federated online reinforcement learning with linear function approximation. While recent multi-agent reinforcement learning algorithms achieve strong regret guarantees, they typically require sharing raw trajectories. This reliance incurs a communication cost that scales linearly with the number of episodes and violates the privacy constraints of federated settings. To address these limitations, we propose Fed-LSVI, the first provably efficient federated algorithm for online reinforcement learning with linear function approximation in episodic Markov decision processes. By integrating

Read original source ↗ Open in workspace

recordType

paper

region

Global