# Rethinking Individual Global Max in Cooperative Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2209.09640 · HTML: https://mlsanity.com/paper/2209.09640/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 20 Sep 2022.

## Built on by (most cited first, 13 of 13)

- [Is Centralized Training with Decentralized Execution Framework Centralized Enough for MARL?](https://mlsanity.com/paper/2305.17352/) (2023)
- [Informed POMDP: Leveraging Additional Information in Model-Based RL](https://mlsanity.com/paper/2306.11488/) (2023)
- [Inferring Latent Temporal Sparse Coordination Graph for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2403.19253/) (2024)
- [The Synergy Between Optimal Transport Theory and Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2401.10949/) (2024)
- [QLLM: Do We Really Need a Mixing Network for Credit Assignment in Multi-Agent Reinforcement Learning?](https://mlsanity.com/paper/2504.12961/) (2025)
- [Hierarchical Multi-Agent Reinforcement Learning with Control Barrier Functions for Safety-Critical Autonomous Systems](https://mlsanity.com/paper/2507.14850/) (2025)
- [Deep incremental learning models for financial temporal tabular datasets with distribution shifts](https://mlsanity.com/paper/2303.07925/) (2023)
- [Computer vision tasks for intelligent aerospace missions: An overview](https://mlsanity.com/paper/2407.06513/) (2024)
- [QFree: A Universal Value Function Factorization for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2311.00356/) (2023)
- [Multi-agent Markov Entanglement](https://mlsanity.com/paper/2506.02385/) (2025)
- [Interactive Distillation for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2601.05407/) (2026)
- [Explicit Credit Assignment through Local Rewards and Dependence Graphs in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2601.21523/) (2026)
- [Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance](https://mlsanity.com/paper/2607.26040/) (2026)

## Abstract (arXiv)

In cooperative multi-agent reinforcement learning, centralized training and decentralized execution (CTDE) has achieved remarkable success. Individual Global Max (IGM) decomposition, which is an important element of CTDE, measures the consistency between local and joint policies. The majority of IGM-based research focuses on how to establish this consistent relationship, but little attention has been paid to examining IGM's potential flaws. In this work, we reveal that the IGM condition is a lossy decomposition, and the error of lossy decomposition will accumulated in hypernetwork-based methods. To address the above issue, we propose to adopt an imitation learning strategy to separate the lossy decomposition from Bellman iterations, thereby avoiding error accumulation. The proposed strategy is theoretically proved and empirically verified on the StarCraft Multi-Agent Challenge benchmark problem with zero sight view. The results also confirm that the proposed method outperforms state-of-the-art IGM-based approaches.