Research map / Multi-agent systems and games / Cooperative multi-agent RL
SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-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 learned alpha_i(s,a_i) with manually preset fixed values near 1.1029 (ablation) | SHAQ · SMAC 5m_vs_6m | win rate | Hurt |
| increase sample size M for approximating alpha (ablation) | SHAQ · SMAC 5m_vs_6m | convergence speed and variance | Mixed |
| use SHAQ instead of SQDDPG (Shapley-based policy gradient) | SMAC 3m/3s5z/3s_vs_5z · SMAC | median test win % | Helped |
| set delta_i=1 for all state-action pairs (reduces SHAQ to VDN) (ablation) | SHAQ · SMAC hard and super-hard maps | median test win % | Hurt |
| SHAQ versus QMIX/QPLEX/QTRAN baselines | SHAQ · SMAC 12 maps | median test win % | Helped |
Closest papers by meaning
- Shapley Q-Value: A Local Reward Approach to Solve Global Reward Games (AAAI 2020 · similarity 0.92)
- Approximating the Shapley Value without Marginal Contributions (AAAI 2024 · similarity 0.87)
- Approximating Shapley Explanations in Reinforcement Learning (NeurIPS 2025 · similarity 0.87)
- STAS: Spatial-Temporal Return Decomposition for Solving Sparse Rewards Problems in Multi-agent Reinforcement Learning (AAAI 2024 · similarity 0.86)
- ConcaveQ: Non-monotonic Value Function Factorization via Concave Representations in Deep Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.86)
- Inverting the Bellman Equation: From $Q$-Values to World Models (NeurIPS 2026 · 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.