Research map / Multi-agent systems and games / Cooperative multi-agent RL
Modeling Others using Oneself 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 online self-policy-based inference of the other agent's goal | SOM · Coin game | average reward | Helped |
| use online self-policy-based inference of the other agent's goal | SOM · Recipe game | winning fraction: ~75-80% vs ~15-20% | Helped |
| use online self-policy-based inference of the other agent's goal | SOM · Door game | winning fraction | Helped |
| increase inference steps from 1 to 5 (ablation) | SOM · Coin game | performance: 6.9% | Helped |
| increase inference steps from 10 to 20 (ablation) | SOM · Coin game | performance: less than 0.45% | Helped |
| use an implicit action-prediction model instead of explicit goal inference | IPP and SPP · Coin game | ability to distinguish Other from Neither coins: about 50% | Hurt |
Closest papers by meaning
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.88)
- Mimicking To Dominate: Imitation Learning Strategies for Success in Multiagent Games (NeurIPS 2024 · similarity 0.87)
- Self-Play $Q$-Learners Can Provably Collude in the Iterated Prisoner's Dilemma (ICML 2025 · similarity 0.86)
- Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations (AAAI 2024 · similarity 0.86)
- Reciprocal Reward Influence Encourages Cooperation From Self-Interested Agents (NeurIPS 2024 · similarity 0.86)
- Learning to Collaborate with Unknown Agents in the Absence of Reward (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.