Research map / Multi-agent systems and games / Cooperative multi-agent RL
FD-MAGRPO: Functionality-Driven Multi-Agent Group Relative Policy Optimization for Analog-LDO Sizing
Haoning Jiang, Han Wu, Zhuoli Ouyang, Ziheng Wang, Tinghuan Chen, Junmin Jiang
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 functionality-based instead of block-based agent grouping (ablation) | MAGRPO · LDO #1 (GSNR step 40) | GSNR: 0.205 -> 0.296 | Improved |
| use functionality-based instead of block-based agent grouping (ablation) | MAGRPO · LDO #2 (GSNR step 5 and 40) | GSNR: 0.204 -> 0.215 at step 40 (+5.4%) | Improved |
| use functionality-based instead of block-based agent grouping (ablation) | MAGRPO · LDO #3 (GSNR step 40) | GSNR: 0.187 -> 0.226 | Improved |
| replace critic-based MAPPO with critic-free MAGRPO (ablation) | multi-agent LDO sizing · LDO #1-#3 reward curves | convergence speed and final reward | Improved |
| use multi-agent MAGRPO instead of single-agent GRPO (ablation) | GRPO · LDO #1-#3 reward curves | reward vs simulations | Improved |
| apply FD-MAGRPO to design LDO #3 from literature | LDO #3 (Guo and Leung 2010) · LDO #3 load regulation | Load Reg. (V/A): 0.12 -> 0.0021 | Improved |
| apply FD-MAGRPO to design LDO #3 from literature | LDO #3 (Guo and Leung 2010) · LDO #3 FoM | FoM (fFV/A): 0.588 -> 0.581 | No clear effect |
Closest papers by meaning
- A Hierarchical Adaptive Multi-Task Reinforcement Learning Framework for Multiplier Circuit Design (ICML 2024 · similarity 0.85)
- Group-in-Group Policy Optimization for LLM Agent Training (NeurIPS 2025 · similarity 0.82)
- ConfigX: Modular Configuration for Evolutionary Algorithms via Multitask Reinforcement Learning (AAAI 2025 · similarity 0.82)
- PPO in the Fisher-Rao geometry (NeurIPS 2026 · similarity 0.82)
- Finite-Time Global Optimality Convergence in Deep Neural Actor-Critic Methods for Decentralized Multi-Agent Reinforcement Learning (ICML 2025 · similarity 0.82)
- Stronger-MAS: Multi-Agent Reinforcement Learning for Collaborative LLMs (ICLR 2026 · similarity 0.81)
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.
