Research map / Federated learning and privacy / Personalized and heterogeneous FL
A Unified Self-Regulating Training Framework for Federated Deep Reinforcement Learning
Meng Xu, Xinhong Chen, Zhongying Chen, Guanyi Zhao, Yang Jin, Jianping Wang
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 |
|---|---|---|---|
| add the self-regulating framework (ST + auxiliary model) | FRD · CartPole (5 clients) | final return: 83.46 -> 174.22 | Improved |
| add the self-regulating framework | FedKL · BipedalWalkerHardcore | final return: 130.39 -> 218.44 | Improved |
| add the self-regulating framework | SCCD · LunarLander | final return: 99.11 -> 240.66 | Improved |
| add the self-regulating framework | FedKL · LunarLander | final return: 265.69 -> 275.08 | Improved |
| add the self-regulating framework | FRL · Humanoid (disturbance 3) | final return: 921.34 -> 4606.58 | Improved |
| add the self-regulating framework | AFedPG · HalfCheetah (disturbance 3) | final return: 5396.47 -> 8036.75 | Improved |
| add the self-regulating framework | FRL · HalfCheetah (disturbance 0) | final return: 10413.22 -> 10365.02 | No clear effect |
| add the self-regulating framework | QAvg · Walker2d (disturbance 3) | final return: 308.05 -> 284.08 | Hurt |
| add auxiliary model to sparse training (ablation) | SCCD · Pendulum | final return: -419.76 -> -290.94 | Improved |
| add sparse training to auxiliary model (ablation) | SCCD · Pendulum | final return: -445.86 -> -290.94 | Improved |
| add auxiliary model to sparse training (ablation) | FedKL · CartPole | final return: 120.27 -> 151.98 | Improved |
| add sparse training to auxiliary model (ablation) | FedKL · CartPole | final return: 105.35 -> 151.98 | Improved |
Closest papers by meaning
- On the Linear Speedup of Personalized Federated Reinforcement Learning with Shared Representations (ICLR 2025 · similarity 0.88)
- Finite-Time Analysis of On-Policy Heterogeneous Federated Reinforcement Learning (ICLR 2024 · similarity 0.87)
- Momentum for the Win: Collaborative Federated Reinforcement Learning across Heterogeneous Environments (ICML 2024 · similarity 0.87)
- Federated Natural Policy Gradient and Actor Critic Methods for Multi-task Reinforcement Learning (NeurIPS 2024 · similarity 0.86)
- Federated Offline Reinforcement Learning: Collaborative Single-Policy Coverage Suffices (ICML 2024 · similarity 0.86)
- Single-Loop Federated Actor-Critic across Heterogeneous Environments (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.
