Research map / Multi-agent systems and games / Cooperative multi-agent RL
Learning to Teach in Cooperative Multiagent 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 |
|---|---|---|---|
| Learn student and teacher policies using VEG advising rewards | LeCTR · Repeated Game | AUC: 272 ± 210 -> 443 ± 3 | Helped |
| Learn student and teacher policies using VEG advising rewards | LeCTR · Hallway Game | AUC: 39 ± 17 -> 71 ± 3 | Helped |
| Learn student and teacher policies using VEG advising rewards | LeCTR · Room Game | AUC: 56 ± 23 -> 79 ± 16 | Helped |
| Use Joint Value Gain instead of VEG (ablation) | LeCTR · Hallway Game | AUC: 71 ± 3 -> 21 ± 31 | Hurt |
| Use Q-Teaching Reward instead of VEG (ablation) | LeCTR · Hallway Game | AUC: 71 ± 3 -> 12 ± 22 | Hurt |
| Use TD Gain instead of VEG (ablation) | LeCTR · Hallway Game | AUC: 71 ± 3 -> 15 ± 25 | Hurt |
| Use Loss Gain instead of VEG (ablation) | LeCTR · Hallway Game | AUC: 71 ± 3 -> 13 ± 22 | Hurt |
| Use Loss Gradient Gain instead of VEG (ablation) | LeCTR · Room Game | AUC: 79 ± 16 -> 56 ± 23 | Hurt |
| Use VEG's thresholded binary advising reward rather than continuous learning-progress rewards (ablation) | LeCTR · Hallway Game | AUC | Helped |
Closest papers by meaning
- Peer Learning: Learning Complex Policies in Groups from Scratch via Action Recommendations (AAAI 2024 · similarity 0.90)
- Cautiously-Optimistic Knowledge Sharing for Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.89)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.88)
- Adaptive Collaboration with Humans: Metacognitive Policy Optimization for Multi-Agent LLMs with Continual Learning (ICLR 2026 · similarity 0.87)
- Cross-environment Cooperation Enables Zero-shot Multi-agent Coordination (ICML 2025 · similarity 0.87)
- Efficient Communication in Multi-Agent Reinforcement Learning with Implicit Consensus Generation (AAAI 2025 · 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.