Research map / Multi-agent systems and games / Cooperative multi-agent RL
Learning to Share and Hide Intentions using Information Regularization
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 |
|---|---|---|---|
| Encourage hiding goal information with action information regularization | Alice in spatial navigation · Spatial navigation | Bob episode length relative to sharing Alice: about 30% longer | Helped |
| Encourage hiding goal information with state information regularization | Alice in spatial navigation · Spatial navigation | Bob episode length relative to sharing Alice: about 30% longer | Helped |
| Encourage Alice to hide goal information | Alice in spatial navigation · Spatial navigation | Frequency Alice beats Bob to the goal: similar magnitude | Helped |
| Encourage Alice to share goal information | Alice in spatial navigation · Spatial navigation | Bob episode length: about 30% shorter relative to hiding Alice | Helped |
| Train without information regularization | Alice in spatial navigation · Spatial navigation | Bob performance | Mixed |
| Encourage hiding information using action information regularization | Alice in the key-and-door game · Key-and-door game | Bob beats or ties Alice to the goal: much less than half the time | Hurt |
| Encourage hiding information using action information regularization | Alice in the key-and-door game · Key-and-door game | Alice picks up the master key: about half of initializations | Helped |
| Encourage sharing goal information | Alice in the key-and-door game · Key-and-door game | Bob beats or ties Alice to the goal: approximately 100% | Hurt |
Closest papers by meaning
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.89)
- Mutual-Information Regularized Multi-Agent Policy Iteration (NeurIPS 2023 · similarity 0.88)
- Learning to Collaborate with Unknown Agents in the Absence of Reward (AAAI 2025 · similarity 0.87)
- Towards Principled Unsupervised Multi-Agent Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- Multi-Agent Learning under Uncertainty: Recurrence vs. Concentration (NeurIPS 2025 · similarity 0.87)
- Generalized Intention Modeling in Multi-Agent Reinforcement Learning (NeurIPS 2026 · 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.