Resilient Consensus-based Multi-agent Reinforcement Learning With Function Approximation
2021 · Martin Figura, Yixuan Lin, Ji Liu, et al.
Abstract
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 \((2H+1)\)-rob
Authors
(none)
Tags
Stats
Related papers
- Provably Efficient Cooperative Multi-agent Reinforcement Learning With Function Approximation (2021)0.00
- Cooperative Multi-agent Reinforcement Learning: Asynchronous Communication And Linear Function Approximation (2023)0.00
- Fully Decentralized Multi-agent Reinforcement Learning With Networked Agents (2018)0.00
- Adversarial Attacks In Consensus-based Multi-agent Reinforcement Learning (2021)0.00
- F2A2: Flexible Fully-decentralized Approximate Actor-critic For Cooperative Multi-agent Reinforcement Learning (2020)0.00
- Distributed Off-policy Actor-critic Reinforcement Learning With Policy Consensus (2019)11.67
- Breaking The Curse Of Multiagency: Provably Efficient Decentralized Multi-agent RL With Function Approximation (2023)0.00
- A Multi-agent Off-policy Actor-critic Algorithm For Distributed Reinforcement Learning (2019)11.39