Research map / Multi-agent systems and games / Cooperative multi-agent RL
Empowering Multi-Robot Cooperation via Sequential World Models
Zijie Zhao, Honglei Guo, Shengqian Chen, Kaixuan Xu, Bo Jiang, Yuanheng Zhu, Dongbin 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 sequential world model vs decentralized (ablation) | SeqWM · Bi-DexHands BottleCap | dynamics and reward prediction error | Improved |
| use sequential world model vs centralized (ablation) | SeqWM · Bi-DexHands BottleCap | dynamics and reward prediction error | No clear effect |
| use concatenation instead of MLP, cross-attention or RNN for communication (ablation) | SeqWM · Bi-DexHands BottleCap | return | Improved |
| use RNN fusion for communication (ablation) | SeqWM · Bi-DexHands BottleCap | return | Hurt |
| add explicit sequential intention sharing (SeqWM vs DecWM) (ablation) | SeqWM · Bi-DexHands BottleCap | return | Improved |
| add world model for trajectory prediction (DecWM vs SeqFree) (ablation) | SeqWM · Bi-DexHands BottleCap | return | Improved |
| add early-stopping heuristic with KL threshold 0.5 (ablation) | SeqWM · planner efficiency | execution time: 57.3% faster, 5.9% performance loss | Improved |
| use SeqWM instead of HASAC, MARIE, MAT, MAPPO | SeqWM · Bi-DexHands and Multi-Quad | return / success rate and sample efficiency | Improved |
Closest papers by meaning
- Revisiting Multi-Agent World Modeling from a Diffusion-Inspired Perspective (NeurIPS 2025 · similarity 0.88)
- POGEMA: A Benchmark Platform for Cooperative Multi-Agent Pathfinding (ICLR 2025 · similarity 0.87)
- Plan-Seq-Learn: Language Model Guided RL for Solving Long Horizon Robotics Tasks (ICLR 2024 · similarity 0.87)
- PWM: Policy Learning with Multi-Task World Models (ICLR 2025 · similarity 0.87)
- World Action Verifier: Self-Improving World Models via Forward-Inverse Asymmetry (NeurIPS 2026 · similarity 0.86)
- Deep Reinforcement Learning for Robotics: A Survey of Real-World Successes (AAAI 2025 · similarity 0.86)
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.
