Research map / Multi-agent systems and games / Cooperative multi-agent RL
An Efficient Transfer Learning Framework for Multiagent Reinforcement Learning
Tianpei Yang, Weixun Wang, Hongyao Tang, Jianye HAO, Zhaopeng Meng, Hangyu Mao, Dong Li, Wulong Liu, Yingfeng Chen, Yujing Hu, Changjie Fan, Chengwei Zhang
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 MAPTF knowledge transfer instead of PPO or DVM | PPO ghosts · Pac-Man OpenClassic | average discounted reward: +2.5 -> +3 | Improved |
| Use MAPTF instead of DVM policy distillation as scenario difficulty increases | PPO · Pac-Man MediumClassic and OriginalClassic | average reward | Improved |
| Add MAPTF to PPO as number of agents grows | PPO · MPE predator-prey | average reward | Improved |
| Add MAPTF to MADDPG and QMIX | MADDPG, QMIX · MPE tasks | average reward | Improved |
| Replace SRO with traditional single-agent option learning (ablation) | MAPTF · MPE (MADDPG, QMIX) | average reward | Improved |
| Use MAPTF w/o SRO instead of training from scratch (ablation) | MADDPG, QMIX · MPE | average reward | Improved |
| Add parameter sharing to MAPTF-PPO (ablation) | MAPTF with PPO · MPE predator-prey | average reward | Mixed |
| Compare MAPTF without PS against PPO with PS (ablation) | MAPTF · MPE predator-prey | average reward | Improved |
Closest papers by meaning
- Optimistic Linear Support and Successor Features as a Basis for Optimal Policy Transfer (ICML 2022 · similarity 0.87)
- A Policy Gradient Algorithm for Learning to Learn in Multiagent Reinforcement Learning (ICML 2021 · similarity 0.87)
- O-MAPL: Offline Multi-agent Preference Learning (ICML 2025 · similarity 0.86)
- Sample-Efficient Multiagent Reinforcement Learning with Reset Replay (ICML 2024 · similarity 0.86)
- Learning Joint Behaviors with Large Variations (AAAI 2025 · similarity 0.85)
- Can RLHF be More Efficient with Imperfect Reward Models? A Policy Coverage Perspective (ICML 2025 · similarity 0.85)
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.
