Research map / Multi-agent systems and games / Cooperative multi-agent RL
Deconfounded Value Decomposition for 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 |
|---|---|---|---|
| add deconfounded value decomposition (trajectory graph proxy confounder) | QPLEX, RODE, QMIX · StarCraft II micro management (SMAC) maps | test win rate | Mixed |
| add deconfounded value decomposition | QMIX, QPLEX · MACO benchmark | test performance | Helped |
| add deconfounded value decomposition | QPLEX, RODE, QMIX · corridor (StarCraft II) | test win rate | No clear effect |
| add deconfounded value decomposition | QMIX · 6h vs 8z (StarCraft II) | mean win rate: 10 to 50 | Helped |
| increase backdoor sampling times D from 1 to 4 to 8 (trajectory graph multi-head) (ablation) | DVD-QPLEX · MMM2 (StarCraft II) | test win rate | Helped |
| set sampling times D=1 (no real backdoor adjustment) versus adding the trajectory graph path (ablation) | QPLEX · MMM2 (StarCraft II) | test win rate | Helped |
Closest papers by meaning
- Value Function Decomposition for Iterative Design of Reinforcement Learning Agents (NeurIPS 2022 · similarity 0.90)
- Locality Matters: A Scalable Value Decomposition Approach for Cooperative Multi-Agent Reinforcement Learning (AAAI 2022 · similarity 0.87)
- Factored Value Functions for Graph-Based Multi-Agent Reinforcement Learning (ICML 2026 · similarity 0.87)
- Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.86)
- REValueD: Regularised Ensemble Value-Decomposition for Factorisable Markov Decision Processes (ICLR 2024 · similarity 0.86)
- STAS: Spatial-Temporal Return Decomposition for Solving Sparse Rewards Problems in Multi-agent Reinforcement Learning (AAAI 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.