Research map / Federated learning and privacy / Privacy attacks and secure learning
Fault-Tolerant Federated Reinforcement Learning with Theoretical Guarantee
Flint Xiaofeng Fan, Yining Ma, Zhongxiang Dai, Wei Jing, Cheston Tan, Bryan Kian Hsiang Low
Read the paperCheck your idea against 137,217 papers
AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.
Measured effects reported in the paper
| What was changed | Where | Measured | Effect |
|---|---|---|---|
| federate K=3 agents instead of a single agent | FedPG-BR · CartPole, LunarLander, HalfCheetah (alpha=0) | mean return | Improved |
| federate K=10 agents instead of K=3 | FedPG-BR · CartPole, LunarLander, HalfCheetah (alpha=0) | mean return | Improved |
| FedPG-BR (K=1) vs GPOMDP | FedPG-BR · three RL tasks | mean return | Improved |
| FedPG-BR (K=1) vs SVRPG | FedPG-BR · three RL tasks | mean return | No clear effect |
| add 3 random-action Byzantine agents to federated GPOMDP | GPOMDP, K=10 · HalfCheetah | mean return | Hurt |
| add 3 Byzantine agents (RN, RA, SF) to federated SVRPG | SVRPG, K=10 · HalfCheetah | mean return | Hurt |
| add 3 Byzantine agents (RN, RA, SF) to FedPG-BR | FedPG-BR, K=10 · HalfCheetah | mean return | No clear effect |
| Byzantine filtering strategy under 3 Byzantine agents vs single agent (ablation) | FedPG-BR, K=10 B=3 · HalfCheetah | mean return | Improved |
| add 3 colluding FedPG attackers knowing the filter | FedPG-BR, K=10 · three RL tasks | mean return | No clear effect |
| FedPG-BR with FedPG attackers vs single-agent FedPG-BR | FedPG-BR, K=10 B=3 · three RL tasks | mean return | Improved |
Closest papers by meaning
- Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning (ICLR 2024 · similarity 0.89)
- Federated Ensemble-Directed Offline Reinforcement Learning (NeurIPS 2024 · similarity 0.88)
- Federated Q-Learning: Linear Regret Speedup with Low Communication Cost (ICLR 2024 · similarity 0.87)
- Single-Loop Federated Actor-Critic across Heterogeneous Environments (AAAI 2025 · similarity 0.87)
- Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices (ICML 2024 · similarity 0.87)
- Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments (ICML 2024 · similarity 0.87)
Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.
