Byzantine-Robust Online and Offline Distributed Reinforcement Learning

Yiding Chen, Xuezhou Zhang, Kaiqing Zhang, Mengdi Wang, Xiaojin Zhu

Research output: Contribution to journalConference articlepeer-review

4 Scopus citations


We consider a distributed reinforcement learning setting where multiple agents separately explore the environment and communicate their experiences through a central server. However, αfraction of agents are adversarial and can report arbitrary fake information. Critically, these adversarial agents can collude and their fake data can be of any sizes. We desire to robustly identify a near-optimal policy for the underlying Markov decision process in the presence of these adversarial agents. Our main technical contribution is COW, a novel algorithm for the robust mean estimation from batches problem, that can handle arbitrary batch sizes. Building upon this new estimator, in the offline setting, we design a Byzantine-robust distributed pessimistic value iteration algorithm; in the online setting, we design a Byzantine-robust distributed optimistic value iteration algorithm. Both algorithms obtain near-optimal sample complexities and achieve superior robustness guarantee than prior works.

Original languageEnglish (US)
Pages (from-to)3230-3269
Number of pages40
JournalProceedings of Machine Learning Research
StatePublished - 2023
Event26th International Conference on Artificial Intelligence and Statistics, AISTATS 2023 - Valencia, Spain
Duration: Apr 25 2023Apr 27 2023

All Science Journal Classification (ASJC) codes

  • Artificial Intelligence
  • Software
  • Control and Systems Engineering
  • Statistics and Probability


Dive into the research topics of 'Byzantine-Robust Online and Offline Distributed Reinforcement Learning'. Together they form a unique fingerprint.

Cite this