# QVMix and QVMix-Max: Extending the Deep Quality-Value Family of Algorithms to Cooperative Multi-Agent Reinforcement Learning

arXiv: https://arxiv.org/abs/2012.12062 · HTML: https://mlsanity.com/paper/2012.12062/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 22 Dec 2020.

## Built on by (most cited first, 5 of 5)

- [Towards a Standardised Performance Evaluation Protocol for Cooperative MARL](https://mlsanity.com/paper/2209.10485/) (2022)
- [Informed POMDP: Leveraging Additional Information in Model-Based RL](https://mlsanity.com/paper/2306.11488/) (2023)
- [IMP-MARL: a Suite of Environments for Large-scale Infrastructure Management Planning via MARL](https://mlsanity.com/paper/2306.11551/) (2023)
- [Value-based CTDE Methods in Symmetric Two-team Markov Game: from Cooperation to Team Competition](https://mlsanity.com/paper/2211.11886/) (2022)
- [Reinformed Dreamer: An Asymmetric World Model Efficiently Trained through Latent Guidance](https://mlsanity.com/paper/2607.26040/) (2026)

## Abstract (arXiv)

This paper introduces four new algorithms that can be used for tackling multi-agent reinforcement learning (MARL) problems occurring in cooperative settings. All algorithms are based on the Deep Quality-Value (DQV) family of algorithms, a set of techniques that have proven to be successful when dealing with single-agent reinforcement learning problems (SARL). The key idea of DQV algorithms is to jointly learn an approximation of the state-value function V, alongside an approximation of the state-action value function Q. We follow this principle and generalise these algorithms by introducing two fully decentralised MARL algorithms (IQV and IQV-Max) and two algorithms that are based on the centralised training with decentralised execution training paradigm (QVMix and QVMix-Max). We compare our algorithms with state-of-the-art MARL techniques on the popular StarCraft Multi-Agent Challenge (SMAC) environment. We show competitive results when QVMix and QVMix-Max are compared to well-known MARL techniques such as QMIX and MAVEN and show that QVMix can even outperform them on some of the tested environments, being the algorithm which performs best overall. We hypothesise that this is due to the fact that QVMix suffers less from the overestimation bias of the Q function.