Research map / Multi-agent systems and games / Cooperative multi-agent RL
Decompose a Task into Generalizable Subtasks in Multi-Agent Reinforcement Learning
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 DT2GS instead of UPDeT for zero-shot deployment without finetuning | DT2GS · SMAC 8 zero-shot scenarios | average test win rate: 22% | Helped |
| use DT2GS instead of ASN_G for zero-shot deployment | DT2GS · SMAC 8 zero-shot scenarios | average test win rate: 34% | Helped |
| finetune DT2GS from source task 3s5z instead of learning target from scratch | DT2GS · 3s5z_vs_3s6z | environment steps to optimal performance: 6 million -> 6400 | Helped |
| transfer DT2GS across tasks versus learning baselines from scratch | DT2GS · SMAC transfer scenarios | convergence speedup: 100× | Helped |
Closest papers by meaning
- AMAGO-2: Breaking the Multi-Task Barrier in Meta-Reinforcement Learning with Transformers (NeurIPS 2024 · similarity 0.90)
- Prioritized Soft Q-Decomposition for Lexicographic Reinforcement Learning (ICLR 2024 · similarity 0.89)
- MoRSE: Task-Oriented Multi-Agent System with Mixture of Role-Subtask Experts (NeurIPS 2026 · similarity 0.88)
- Generalizable Task Representation Learning for Offline Meta-Reinforcement Learning with Data Limitations (AAAI 2024 · similarity 0.88)
- Decomposed Prompt Decision Transformer for Efficient Unseen Task Generalization (NeurIPS 2024 · similarity 0.88)
- Learning Generalizable Skills from Offline Multi-Task Data for Multi-Agent Cooperation (ICLR 2025 · similarity 0.87)
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.