Research map / Multi-agent systems and games / Cooperative multi-agent RL
Unreal-MAP: Unreal-Engine-Based General Platform for Multi-agent Reinforcement Learning
Tianyi Hu, Qingxu Fu, Zhiqiang Pu, Yuan Wang, Tenghai Qiu
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 |
|---|---|---|---|
| increase time dilation factor in Unreal-MAP (ablation) | Unreal-MAP · resource consumption | CPU / memory / GPU memory | Mixed |
| count 1280 physics frames per timestep in Unreal-MAP | Unreal-MAP · efficiency comparison | FPS (x10^3): 9.67 -> 1340 (vs SMAC) | Improved |
| Unreal-MAP versus MPE and SMAC | Unreal-MAP · efficiency comparison | TPS (x10^3): 1.04 vs 1.21 (SMAC), 1.62 (MPE) | No clear effect |
| Unreal-MAP versus Unity-ML Agents | Unreal-MAP · efficiency comparison | TPS (x10^3): 10.2 -> 1.04 | Hurt |
| Unreal-MAP versus Unity-ML Agents | Unreal-MAP · efficiency comparison | CPU utilization (%): 25.6 -> 8.9 | Improved |
| Unreal-MAP versus SMAC | Unreal-MAP · efficiency comparison | memory (GB): 33.5 -> 13.6 | Improved |
| Unreal-MAP versus MPE | Unreal-MAP · efficiency comparison | memory (GB): 3.9 -> 13.6 | Hurt |
| deploy policy trained in Unreal-MAP digital twin to real hardware | navigation game policy · sim2real navigation game | success rate (%): 94.1 -> 93.3 | No clear effect |
| modify agent properties, types, number, or teams in the same scenario | Unreal-MAP example tasks · 15 example tasks | test win rate | Improved |
Closest papers by meaning
- Dispelling the Mirage of Progress in Offline MARL through Standardised Baselines and Evaluation (NeurIPS 2024 · similarity 0.88)
- Foundations of Multi-Agent Learning in Dynamic Environments: Where Reinforcement Learning Meets Strategic Decision-Making (AAAI 2025 · similarity 0.87)
- FightLadder: A Benchmark for Competitive Multi-Agent Reinforcement Learning (ICML 2024 · similarity 0.86)
- ComaDICE: Offline Cooperative Multi-Agent Reinforcement Learning with Stationary Distribution Shift Regularization (ICLR 2025 · similarity 0.86)
- JaxMARL: Multi-Agent RL Environments and Algorithms in JAX (NeurIPS 2024 · similarity 0.86)
- Dr. MAS: Stable Reinforcement Learning for Multi-Agent LLM Systems (NeurIPS 2026 · 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.
