Research map / Multi-agent systems and games / Cooperative multi-agent RL
Inter-Agent Relative Representations for Multi-Agent Option Discovery
Raul D. Steleac, Mohan Sridharan, David Abel
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 |
|---|---|---|---|
| add IARO joint options to IQL | IQL · LBF and Overcooked | apples eaten / deliveries per episode (IQM) | Improved |
| use IARO options instead of VDN | IQL+IARO · Overcooked Forced Coordination | deliveries per episode | Hurt |
| discover options on relative representation instead of raw joint states or Kronecker products (ablation) | IQL+IARO · LBF and Overcooked | downstream performance | Improved |
| use multi-dimensional n-distance instead of scalar (ablation) | IQL+IARO · LBF | downstream performance | No clear effect |
| use multi-dimensional n-distance instead of scalar (ablation) | IQL+IARO · Overcooked | downstream performance | Improved |
| increase number of options beyond a small set (ablation) | IQL+IARO · LBF and Overcooked | downstream performance | Mixed |
Closest papers by meaning
- Scalable Multi-agent Covering Option Discovery based on Kronecker Graphs (NeurIPS 2022 · similarity 0.91)
- MALinZero: Efficient Low-Dimensional Search for Mastering Complex Multi-Agent Planning (NeurIPS 2025 · similarity 0.86)
- Graph Diffusion for Robust Multi-Agent Coordination (ICML 2025 · similarity 0.86)
- Imagine, Initialize, and Explore: An Effective Exploration Method in Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.86)
- COMPLLLM: Fine-tuning LLMs to Discover Complementary Signals for Decision-making (NeurIPS 2026 · similarity 0.85)
- Emergent Coordination in Multi-Agent Language Models (ICLR 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.
