Research map / Multi-agent systems and games / Cooperative multi-agent RL
Multi-Agent Reinforcement Learning is a Sequence Modeling Problem
Read the paperCheck your idea against 108,967 papers
AI-extracted summary. Written by AI from the paper's title only (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 MAT instead of MAPPO for few-shot adaptation | SMAC 27m vs 30m · SMAC 27m vs 30m | median evaluation win rate: 26.2 vs 53.8 | Helped |
| Pre-train MAT rather than train MAT from scratch | SMAC 27m vs 30m · SMAC 27m vs 30m | median evaluation win rate: 0.0 vs 53.8 | Helped |
| Use MAT instead of MAPPO for few-shot adaptation | Multi-Agent MuJoCo back shin · Multi-Agent MuJoCo back shin | average evaluation score: 2796 vs 6077 | Helped |
| Use agent-ID encoding instead of sequence-position encoding (ablation) | MAT · HalfCheetah | episodic reward | Helped |
| Add position encoding on top of agent-ID encoding (ablation) | MAT · HalfCheetah | episodic reward | No clear effect |
| Use the full encoder-decoder Transformer instead of decoder only (ablation) | MAT · Homogeneous and heterogeneous MARL scenarios | performance | Helped |
| Use the full encoder-decoder Transformer instead of encoder only (ablation) | MAT · Homogeneous and heterogeneous MARL scenarios | performance | Helped |
| Use the full Transformer instead of GRU-based encoder and decoder (ablation) | MAT · Homogeneous and heterogeneous MARL scenarios | performance | Helped |
Closest papers by meaning
- Sequential Order Adjustment of Action Decisions for Multi-Agent Transformer (Student Abstract) (AAAI 2025 · similarity 0.91)
- Towards Efficient Collaboration via Graph Modeling in Reinforcement Learning (AAAI 2025 · similarity 0.90)
- Grounded Answers for Multi-agent Decision-making Problem through Generative World Model (NeurIPS 2024 · similarity 0.89)
- Bridging Training and Execution via Dynamic Directed Graph-Based Communication in Cooperative Multi-Agent Systems (AAAI 2025 · similarity 0.88)
- Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective (NeurIPS 2025 · similarity 0.88)
- Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems (NeurIPS 2026 · similarity 0.88)
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.