Research map / Multi-agent systems and games / Cooperative multi-agent RL
Shapley Q-Value: A Local Reward Approach to Solve Global Reward Games
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 Shapley Q-value local credit (SQDDPG) instead of shared-reward MADDPG | MADDPG · Traffic Junction medium | success rate: 87.92% -> 88.98% | Helped |
| use Shapley Q-value local credit (SQDDPG) instead of shared-reward MADDPG | MADDPG · Traffic Junction hard | success rate: 84.21% -> 87.04% | Helped |
| use Shapley Q-value local credit (SQDDPG) instead of shared-reward MADDPG | MADDPG · Traffic Junction easy | success rate: 93.72% -> 93.26% | No clear effect |
| use Shapley Q-value instead of COMA marginal-contribution credit | COMA · Prey-and-Predator credit assignment | Pearson correlation: 0.1274 -> 0.3210 | Helped |
| increase Shapley Q-value sample size M (ablation) | SQDDPG · Cooperative Navigation | convergence rate | Helped |
| use SQDDPG instead of baselines | MADDPG/IDDPG/COMA/IA2C · Cooperative Navigation | convergence rate | Helped |
Closest papers by meaning
- SHAQ: Incorporating Shapley Value Theory into Multi-Agent Q-Learning (NeurIPS 2022 · similarity 0.92)
- STAS: Spatial-Temporal Return Decomposition for Solving Sparse Rewards Problems in Multi-agent Reinforcement Learning (AAAI 2024 · similarity 0.88)
- Sequential Solution Concepts in Cooperative Games with Generalized Characteristic Functions (NeurIPS 2026 · similarity 0.87)
- Learning the Expected Core of Strictly Convex Stochastic Cooperative Games (NeurIPS 2024 · similarity 0.87)
- Approximating the Shapley Value without Marginal Contributions (AAAI 2024 · similarity 0.86)
- Learning Equilibria in Adversarial Team Markov Games: A Nonconvex-Hidden-Concave Min-Max Optimization Problem (NeurIPS 2024 · 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.