# Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation

arXiv: https://arxiv.org/abs/2009.11146 · HTML: https://mlsanity.com/paper/2009.11146/

## Key facts

- Cited by 3 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 23 Sep 2020.

## Built on by (most cited first, 3 of 3)

- [The Blessing of Heterogeneity in Federated Q-Learning: Linear Speedup and Beyond](https://mlsanity.com/paper/2305.10697/) (2023)
- [Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation](https://mlsanity.com/paper/2111.06776/) (2021)
- [Fully Byzantine-Resilient Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2609.25701/) (2026)

## Abstract (arXiv)

This paper considers the policy evaluation problem in a multi-agent reinforcement learning (MARL) environment over decentralized and directed networks. The focus is on decentralized temporal difference (TD) learning with linear function approximation in the presence of unreliable or even malicious agents, termed as Byzantine agents. In order to evaluate the quality of a fixed policy in a common environment, agents usually run decentralized TD(λ) collaboratively. However, when some Byzantine agents behave adversarially, decentralized TD(λ) is unable to learn an accurate linear approximation for the true value function. We propose a trimmed-mean based Byzantine-resilient decentralized TD(λ) algorithm to perform policy evaluation in this setting. We establish the finite-time convergence rate, as well as the asymptotic learning error in the presence of Byzantine agents. Numerical experiments corroborate the robustness of the proposed algorithm.