# AI for Explaining Decisions in Multi-Agent Environments

arXiv: https://arxiv.org/abs/1910.04404 · HTML: https://mlsanity.com/paper/1910.04404/

## Key facts

- Cited by 12 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 10 Oct 2019.

## Built on by (most cited first, 12 of 12)

- [Toward Policy Explanations for Multi-Agent Reinforcement Learning](https://mlsanity.com/paper/2204.12568/) (2022)
- [Explaining Preference-driven Schedules: the EXPRES Framework](https://mlsanity.com/paper/2203.08895/) (2022)
- [Justifying Social-Choice Mechanism Outcome for Improving Participant Satisfaction](https://mlsanity.com/paper/2205.15863/) (2022)
- [Contrastive Explanations of Centralized Multi-agent Optimization Solutions](https://mlsanity.com/paper/2308.05984/) (2023)
- [Efficiently Quantifying Individual Agent Importance in Cooperative MARL](https://mlsanity.com/paper/2312.08466/) (2023)
- [Explaining Decisions of Agents in Mixed-Motive Games](https://mlsanity.com/paper/2407.15255/) (2024)
- [ADESSE: Advice Explanations in Complex Repeated Decision-Making Environments](https://mlsanity.com/paper/2405.20705/) (2024)
- [High-order Interactions Modeling for Interpretable Multi-Agent Q-Learning](https://mlsanity.com/paper/2510.20218/) (2025)
- [Explaining Ridesharing: Selection of Explanations for Increasing User Satisfaction](https://mlsanity.com/paper/2105.12500/) (2021)
- [Behave-XAI: Deep Explainable Learning of Behavioral Representational Data](https://mlsanity.com/paper/2301.00016/) (2022)
- [From DDMs to DNNs: Using process data and models of decision-making to improve human-AI interactions](https://mlsanity.com/paper/2308.15225/) (2023)
- [Explaining Strategic Decisions in Multi-Agent Reinforcement Learning for Aerial Combat Tactics](https://mlsanity.com/paper/2505.11311/) (2025)

## Abstract (arXiv)

Explanation is necessary for humans to understand and accept decisions made by an AI system when the system's goal is known. It is even more important when the AI system makes decisions in multi-agent environments where the human does not know the systems' goals since they may depend on other agents' preferences. In such situations, explanations should aim to increase user satisfaction, taking into account the system's decision, the user's and the other agents' preferences, the environment settings and properties such as fairness, envy and privacy. Generating explanations that will increase user satisfaction is very challenging; to this end, we propose a new research direction: xMASE. We then review the state of the art and discuss research directions towards efficient methodologies and algorithms for generating explanations that will increase users' satisfaction from AI system's decisions in multi-agent environments.