Research map / Multi-agent systems and games / Cooperative multi-agent RL
MARLIN: Multi-Agent Reinforcement Learning for Incremental DAG Discovery
Dong Li, Zhengzhang Chen, Xujiang Zhao, Linlin Yu, Zhong Chen, Yi He, Haifeng Chen, Chen Zhao
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 two agents (state-specific + state-invariant) instead of single agent (ablation) | MARLIN · Synthetic LG d=100 | SHD: 180.6 -> 105.5 | Improved |
| use two agents instead of single agent (ablation) | MARLIN · Synthetic LG d=20 | SHD: 14.5 -> 5.24 (ATB 16 -> 26) | Improved |
| use two agents instead of single agent (ablation) | MARLIN · Synthetic LG d=100 | time per batch: 1687 -> 1321 | Improved |
| parallelize via factored action space (MARLIN-M) | MARLIN · Synthetic QR | ATB / SHD: ATB 81 -> 32; SHD 7.0 -> 14.2 | Mixed |
| parallelize via factored action space (MARLIN-M) | MARLIN · OnlineBoutique RCA | MRR / ATC: MRR 76.4% -> 67.6%; ATC 63 -> 25 | Mixed |
| MARLIN vs strongest RL baseline RCL-OG | MARLIN · Synthetic QR | SHD: 15.6 -> 7.0 | Improved |
| MARLIN vs CORL at d=100 on TPR | MARLIN · Synthetic LG d=100 | TPR | Hurt |
Closest papers by meaning
- DAGent: Evaluate-then-Grow Planning for Deep Research Agents (NeurIPS 2026 · similarity 0.85)
- Novelty-Guided Data Reuse for Efficient and Diversified Multi-Agent Reinforcement Learning (AAAI 2025 · similarity 0.85)
- Sequential Order Adjustment of Action Decisions for Multi-Agent Transformer (Student Abstract) (AAAI 2025 · similarity 0.85)
- Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation (NeurIPS 2024 · similarity 0.85)
- Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems (AAAI 2025 · similarity 0.85)
- Bayesian Ego-graph inference for Networked Multi-Agent Reinforcement Learning (NeurIPS 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.
