# Resilient Consensus-based Multi-agent Reinforcement Learning with Function Approximation

arXiv: https://arxiv.org/abs/2111.06776 · HTML: https://mlsanity.com/paper/2111.06776/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 19 of its 40 references that are in the map.
- First posted on arXiv 12 Nov 2021.

## Builds on (most cited first, 19 of 19)

- [Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments](https://mlsanity.com/paper/1706.02275/) (2017)
- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Multi-Agent Reinforcement Learning: A Selective Overview of Theories and Algorithms](https://mlsanity.com/paper/1911.10635/) (2019)
- [Monotonic Value Function Factorisation for Deep Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2003.08839/) (2020)
- [Fully Decentralized Multi-Agent Reinforcement Learning with Networked Agents](https://mlsanity.com/paper/1802.08757/) (2018)
- [Generalized Byzantine-tolerant SGD](https://mlsanity.com/paper/1802.10116/) (2018)
- [Byzantine Stochastic Gradient Descent](https://mlsanity.com/paper/1803.08917/) (2018)
- [Distributed Statistical Machine Learning in Adversarial Settings: Byzantine Gradient Descent](https://mlsanity.com/paper/1705.05491/) (2017)
- [Reinforcement Learning in Economics and Finance](https://mlsanity.com/paper/2003.10014/) (2020)
- [Deep Reinforcement Learning for Swarm Systems](https://mlsanity.com/paper/1807.06613/) (2018)
- [A Multi-Agent Off-Policy Actor-Critic Algorithm for Distributed Reinforcement Learning](https://mlsanity.com/paper/1903.06372/) (2019)
- [Distributed Optimization Under Adversarial Nodes](https://mlsanity.com/paper/1606.08939/) (2016)
- [Value Propagation for Decentralized Networked Deep Multi-agent Reinforcement Learning](https://mlsanity.com/paper/1901.09326/) (2019)
- [Adversarial attacks in consensus-based multi-agent reinforcement learning](https://mlsanity.com/paper/2103.06967/) (2021)
- [A Communication-Efficient Multi-Agent Actor-Critic Algorithm for Distributed Reinforcement Learning](https://mlsanity.com/paper/1907.03053/) (2019)
- [Variance Reduced Median-of-Means Estimator for Byzantine-Robust Distributed Inference](https://mlsanity.com/paper/2103.02860/) (2021)
- [Iterative Byzantine Vector Consensus in Incomplete Graphs](https://mlsanity.com/paper/1307.2483/) (2013)
- [Towards Resilience for Multi-Agent QD-Learning](https://mlsanity.com/paper/2104.03153/) (2021)
- [Byzantine-Resilient Decentralized TD Learning with Linear Function Approximation](https://mlsanity.com/paper/2009.11146/) (2020)

## Built on by (most cited first, 1 of 1)

- [Cooperative Actor-Critic via TD Error Aggregation](https://mlsanity.com/paper/2207.12533/) (2022)

## Abstract (arXiv)

Adversarial attacks during training can strongly influence the performance of multi-agent reinforcement learning algorithms. It is, thus, highly desirable to augment existing algorithms such that the impact of adversarial attacks on cooperative networks is eliminated, or at least bounded. In this work, we consider a fully decentralized network, where each agent receives a local reward and observes the global state and action. We propose a resilient consensus-based actor-critic algorithm, whereby each agent estimates the team-average reward and value function, and communicates the associated parameter vectors to its immediate neighbors. We show that in the presence of Byzantine agents, whose estimation and communication strategies are completely arbitrary, the estimates of the cooperative agents converge to a bounded consensus value with probability one, provided that there are at most H Byzantine agents in the neighborhood of each cooperative agent and the network is (2H+1)-robust. Furthermore, we prove that the policy of the cooperative agents converges with probability one to a bounded neighborhood around a local maximizer of their team-average objective function under the assumption that the policies of the adversarial agents asymptotically become stationary.