|
| | | | |
| | | |
| Stat |
Members: 3657
Articles: 2'599'751
Articles rated: 2609
14 October 2024 |
|
| | | | |
|
Article overview
| |
|
|
Byzantine-Robust Online and Offline Distributed Reinforcement Learning | | Yiding Chen
; Xuezhou Zhang
; Kaiqing Zhang
; Mengdi Wang
; Xiaojin Zhu
; | | Date: |
1 Jun 2022 | | Abstract: | We consider a distributed reinforcement learning setting where multiple
agents separately explore the environment and communicate their experiences
through a central server. However, $alpha$-fraction 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
Weighted-Clique, 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. | | Source: | arXiv, 2206.00165 | | Services: | Forum | Review | PDF | Favorites | |
|
|
No review found.
Did you like this article?
Note: answers to reviews or questions about the article must be posted in the forum section.
Authors are not allowed to review their own article. They can use the forum section.
|
| |
|
|
|
REGISTER