# MAGIC-MASK: Multi-Agent Guided Inter-Agent Collaboration with Mask-Based Explainability for Reinforcement Learning

arXiv: https://arxiv.org/abs/2510.00274 · HTML: https://mlsanity.com/paper/2510.00274/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 15 of its 31 references that are in the map.
- First posted on arXiv 30 Sep 2025.

## Builds on (most cited first, 15 of 15)

- [Counterfactual Multi-Agent Policy Gradients](https://mlsanity.com/paper/1705.08926/) (2017)
- [Counterfactual Visual Explanations](https://mlsanity.com/paper/1904.07451/) (2019)
- [Revisiting the Arcade Learning Environment: Evaluation Protocols and Open Problems for General Agents](https://mlsanity.com/paper/1709.06009/) (2017)
- [Google Research Football: A Novel Reinforcement Learning Environment](https://mlsanity.com/paper/1907.11180/) (2019)
- [Problems with Shapley-value-based explanations as feature importance measures](https://mlsanity.com/paper/2002.11097/) (2020)
- [DouZero: Mastering DouDizhu with Self-Play Deep Reinforcement Learning](https://mlsanity.com/paper/2106.06135/) (2021)
- [Generating Adjacency-Constrained Subgoals in Hierarchical Reinforcement Learning](https://mlsanity.com/paper/2006.11485/) (2020)
- [Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution](https://mlsanity.com/paper/1912.12191/) (2019)
- [Establishing Appropriate Trust via Critical States](https://mlsanity.com/paper/1810.08174/) (2018)
- [Shapley Counterfactual Credits for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2106.00285/) (2021)
- [Multi-agent Reinforcement Learning: A Comprehensive Survey](https://mlsanity.com/paper/2312.10256/) (2023)
- [Maximize to Explore: One Objective Function Fusing Estimation, Planning, and Exploration](https://mlsanity.com/paper/2305.18258/) (2023)
- [TripleTree: A Versatile Interpretable Representation of Black Box Agents and their Environments](https://mlsanity.com/paper/2009.04743/) (2020)
- [Proactive Multi-Camera Collaboration For 3D Human Pose Estimation](https://mlsanity.com/paper/2303.03767/) (2023)
- [Understanding Individual Agent Importance in Multi-Agent System via Counterfactual Reasoning](https://mlsanity.com/paper/2412.15619/) (2024)

## Abstract (arXiv)

Understanding the decision-making process of Deep Reinforcement Learning agents remains a key challenge for deploying these systems in safety-critical and multi-agent environments. While prior explainability methods like StateMask, have advanced the identification of critical states, they remain limited by computational cost, exploration coverage, and lack of adaptation to multi-agent settings. To overcome these limitations, we propose a mathematically grounded framework, MAGIC-MASK (Multi-Agent Guided Inter-agent Collaboration with Mask-Based Explainability for Reinforcement Learning), that extends perturbation-based explanation to Multi-Agent Reinforcement Learning. Our method integrates Proximal Policy Optimization, adaptive epsilon-greedy exploration, and lightweight inter-agent collaboration to share masked state information and peer experience. This collaboration enables each agent to perform saliency-guided masking and share reward-based insights with peers, reducing the time required for critical state discovery, improving explanation fidelity, and leading to faster and more robust learning. The core novelty of our approach lies in generalizing explainability from single-agent to multi-agent systems through a unified mathematical formalism built on trajectory perturbation, reward fidelity analysis, and Kullback-Leibler divergence regularization. This framework yields localized, interpretable explanations grounded in probabilistic modeling and multi-agent Markov decision processes. We validate our framework on both single-agent and multi-agent benchmarks, including a multi-agent highway driving environment and Google Research Football, demonstrating that MAGIC-MASK consistently outperforms state-of-the-art baselines in fidelity, learning efficiency, and policy robustness while offering interpretable and transferable explanations.