Research map / Multi-agent systems and games / Cooperative multi-agent RL
Greedy based Value Representation for Optimal Coordination in 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 |
|---|---|---|---|
| Use inferior target shaping (ITS) instead of the unshaped VDN representation (ablation) | Value decomposition · One-step matrix games | optimal-node STN ratio: VDN: 0 when ε>0.8; ITS: >0 always | Helped |
| Apply ITS and sufficiently large exploration (ablation) | Value decomposition · One-step matrix games | optimal STN ratio: ε0=0.837; R_STN_opt=1 | Helped |
| Add superior experience replay (SER) to ITS (ablation) | GVR · Matrix games | optimal consistency | Helped |
| Use GVR rather than QTRAN, QPLEX, or CWQMIX | Matrix games 3^2, 6^3, and 12^4 · Matrix games 3^2, 6^3, and 12^4 | median test return: 8 | Helped |
| Use GVR rather than VDN, QMIX, QPLEX, or WQMIX | Predator-prey · Predator-prey under three punishment values | task performance | Helped |
| Use GVR rather than the baselines | SMAC · StarCraft Multi-agent Challenge | task performance | Helped |
| Enable the adaptive trade-off through ensemble critics (ablation) | GVR · Some challenging SMAC tasks | task performance | Hurt |
| Use large exploration without ITS (ablation) | Linear value decomposition · One-step matrix games | optimal consistency: ε>0.857 | No clear effect |
Closest papers by meaning
- Non-Linear Coordination Graphs (NeurIPS 2022 · similarity 0.89)
- Beyond Monotonicity: Revisiting Factorization Principles in Multi-Agent Q-Learning (AAAI 2026 · similarity 0.89)
- Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning (ICLR 2026 · similarity 0.89)
- Value Function Decomposition for Iterative Design of Reinforcement Learning Agents (NeurIPS 2022 · similarity 0.88)
- Optimistic Value Instructors for Cooperative Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.88)
- ConcaveQ: Non-monotonic Value Function Factorization via Concave Representations in Deep Multi-Agent Reinforcement Learning (AAAI 2024 · similarity 0.88)
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.