MAGIC-MASK: Multi-agent Guided Inter-agent Collaboration With Mask-based Explainability For Reinforcement Learning
2025 · Maisha Maliha, Dean Hougen
Abstract
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 re
Authors
(none)
Tags
Stats
Related papers
- Why The Agent Made That Decision: Contrastive Explanation Learning For Reinforcement Learning (2024)0.00
- An Organizationally-oriented Approach To Enhancing Explainability And Control In Multi-agent Reinforcement Learning (2025)2.26
- MACIE: Multi-agent Causal Intelligence Explainer For Collective Behavior Understanding (2025)2.26
- Unveiling The Black Box: A Multi-layer Framework For Explaining Reinforcement Learning-based Cyber Agents (2025)0.00
- Masked Autoencoding For Scalable And Generalizable Decision Making (2022)0.00
- Talktoagent: A Human-centric Explanation Of Reinforcement Learning Agents With Large Language Models (2025)0.00
- Perspectives For Direct Interpretability In Multi-agent Deep Reinforcement Learning (2025)0.00
- Strategy Masking: A Method For Guardrails In Value-based Reinforcement Learning Agents (2025)0.00