Research map / Multi-agent systems and games / Cooperative multi-agent RL
Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient
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 polarization joint action values for explicit credit assignment | MAPPG · Modified matrix game | convergence to the global optimum | Helped |
| Use polarization policy gradients | MAPPG · MTQ differential game | convergence to the global optimum | Helped |
| Use MAPPG instead of the tested MAPG baselines | SMAC · Eight StarCraft II maps | final performance | Helped |
| Remove polarization joint action values (ablation) | MAPPG on SMAC · 3s_vs_4z | convergence | Hurt |
| Add polarization joint action values (ablation) | MAPPG on SMAC · 3s_vs_4z | convergence | Helped |
| Remove the pessimistic bound (ablation) | MAPPG on SMAC · 3s_vs_4z | policy improvement stability | Hurt |
| Add the pessimistic bound (ablation) | MAPPG on SMAC · 3s_vs_4z | policy improvement stability | Helped |
| Increase the enlargement factor α (ablation) | MAPPG · MTQ differential game | reward closeness to the optimal reward | Helped |
| Use α=1 or α=2 rather than the other tested enlargement factors (ablation) | MAPPG · MTQ differential game | convergence | Hurt |
Closest papers by meaning
- Learning Implicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning (NeurIPS 2020 · similarity 0.92)
- Revisiting Some Common Practices in Cooperative Multi-Agent Reinforcement Learning (ICML 2022 · similarity 0.90)
- TAPE: Leveraging Agent Topology for Cooperative Multi-Agent Policy Gradient (AAAI 2024 · similarity 0.88)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.87)
- Optimistic Multi-Agent Policy Gradient (ICML 2024 · similarity 0.87)
- Fair Cooperation in Mixed-Motive Games via Conflict-Aware Gradient Adjustment (NeurIPS 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.