Research map / Multi-agent systems and games / Cooperative multi-agent RL
Learning Implicit Credit Assignment for Cooperative 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 |
|---|---|---|---|
| replace the mixing critic hypernetwork with an MLP critic (ablation) | LICA · SMAC 5m_vs_6m | win rate | Hurt |
| feed action distribution parameters to the critic instead of Gumbel-Softmax sampled actions (ablation) | LICA · SMAC 5m_vs_6m | win rate | Helped |
| use adaptive entropy regularization instead of vanilla entropy regularization (ablation) | LICA · SMAC 5m_vs_6m | win rate | Helped |
| use mixing critic and Gumbel sampling variant ablations on other maps (ablation) | LICA · SMAC 2c_vs_64zg and MMM2 | win rate | Helped |
Closest papers by meaning
- Learning Explicit Credit Assignment for Cooperative Multi-Agent Reinforcement Learning via Polarization Policy Gradient (AAAI 2023 · similarity 0.92)
- Difference Advantage Estimation for Multi-Agent Policy Gradients (ICML 2022 · similarity 0.89)
- FACMAC: Factored Multi-Agent Centralised Policy Gradients (NeurIPS 2021 · similarity 0.89)
- Multi-agent cooperation through learning-aware policy gradients (ICLR 2025 · similarity 0.89)
- Multi-Agent Actor-Critic for Mixed Cooperative-Competitive Environments (NeurIPS 2017 · similarity 0.89)
- COSAC: Counterfactual Credit Assignment in Sequential Cooperative Teams (NeurIPS 2026 · similarity 0.89)
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.