Research map / Reinforcement learning / MDPs and planning
Client Selection for Federated Policy Optimization with Environment Heterogeneity
Zhijie Xie, Shenghui Song
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 |
|---|---|---|---|
| use FedPOHCS client selection instead of Power-of-Choice | federated policy optimization · Hoppers (medium heterogeneity) | rounds to reach reward 1450: 80 -> 20 | Improved |
| use one-phase communication-efficient scheme instead of two-phase (ablation) | FedPOHCS · Mountain Cars (medium heterogeneity) | final return and early stability | Mixed |
| increase environment heterogeneity from low to high (ablation) | all selection methods incl. FedPOHCS · Mountain Cars | return | Hurt |
| increase environment heterogeneity (FedAvg random selection vs biased selection) (ablation) | FedAvg, Power-of-Choice, GradientNorm, FedPOHCS · Hoppers | return | Mixed |
Closest papers by meaning
- Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments (ICML 2024 · similarity 0.90)
- Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning (ICLR 2024 · similarity 0.90)
- Single-Loop Federated Actor-Critic across Heterogeneous Environments (AAAI 2025 · similarity 0.88)
- Asynchronous Federated Reinforcement Learning with Policy Gradient Updates: Algorithm Design and Convergence Analysis (ICLR 2025 · similarity 0.87)
- Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning (NeurIPS 2024 · similarity 0.87)
- Reinforcement Active Client Selection for Federated Heterogeneous Graph Learning (AAAI 2025 · similarity 0.86)
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.
