# NA2Q: Neural Attention Additive Model for Interpretable Multi-Agent Q-Learning

arXiv: https://arxiv.org/abs/2304.13383 · HTML: https://mlsanity.com/paper/2304.13383/

## Key facts

- Cited by 14 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Apr 2023.

## Built on by (most cited first, 14 of 14)

- [TimeX++: Learning Time-Series Explanations with Information Bottleneck](https://mlsanity.com/paper/2405.09308/) (2024)
- [Explaining Time Series via Contrastive and Locally Sparse Perturbations](https://mlsanity.com/paper/2401.08552/) (2024)
- [A Comprehensive Survey on Self-Interpretable Neural Networks](https://mlsanity.com/paper/2501.15638/) (2025)
- [Individual Contributions as Intrinsic Exploration Scaffolds for Multi-agent Reinforcement Learning](https://mlsanity.com/paper/2405.18110/) (2024)
- [Retaining Suboptimal Actions to Follow Shifting Optima in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2602.17062/) (2026)
- [Higher Replay Ratio Empowers Sample-Efficient Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2404.09715/) (2024)
- [High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning](https://mlsanity.com/paper/2510.20218/) (2025)
- [Learning Individual Intrinsic Reward in Multi-Agent Reinforcement Learning via Incorporating Generalized Human Expertise](https://mlsanity.com/paper/2507.18867/) (2025)
- [Concept Learning for Cooperative Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2507.20143/) (2025)
- [Understanding Action Effects through Instrumental Empowerment in Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2508.15652/) (2025)
- [PACT: Phenotype-Aware Contrastive Team Representation for Multi-Phenotype Grouped Ad Hoc Teamwork](https://mlsanity.com/paper/2510.25340/) (2025)
- [Embedded Safety-Aligned Intelligence via Differentiable Internal Alignment Embeddings](https://mlsanity.com/paper/2512.18309/) (2025)
- [Breakthrough the Suboptimal Stable Point in Value-Factorization-Based Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2604.05297/) (2026)
- [Escaping Local Views: Discovering Latent Concepts for Interpretable Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2609.34459/) (2026)

## Abstract (arXiv)

Value decomposition is widely used in cooperative multi-agent reinforcement learning, however, its implicit credit assignment mechanism is not yet fully understood due to black-box networks. In this work, we study an interpretable value decomposition framework via the family of generalized additive models. We present a novel method, named Neural Attention Additive Q-learning (NA2Q), providing inherent intelligibility of collaboration behavior. NA2Q can explicitly factorize the optimal joint policy induced by enriching shape functions to model all possible coalitions of agents into individual policies. Moreover, we construct identity semantics to promote estimating credits together with the global state and individual value functions, where local semantic masks help us diagnose whether each agent captures relevant-task information. Extensive experiments show that NA2Q consistently achieves superior performance compared to different state-of-the-art methods on all challenging tasks, while yielding human-like interpretability.