# Quality Diversity Evolutionary Learning of Decision Trees

arXiv: https://arxiv.org/abs/2208.12758 · HTML: https://mlsanity.com/paper/2208.12758/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 51 references that are in the map.
- First posted on arXiv 17 Aug 2022.

## Builds on (most cited first, 26 of 26)

- [Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actor](https://mlsanity.com/paper/1801.01290/) (2018)
- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [Mastering Atari, Go, Chess and Shogi by Planning with a Learned Model](https://mlsanity.com/paper/1911.08265/) (2019)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [Illuminating search spaces by mapping elites](https://mlsanity.com/paper/1504.04909/) (2015)
- [Interpretable Machine Learning: Fundamental Principles and 10 Grand Challenges](https://mlsanity.com/paper/2103.11251/) (2021)
- [Deep Learning: A Critical Appraisal](https://mlsanity.com/paper/1801.00631/) (2018)
- [Robots that can adapt like animals](https://mlsanity.com/paper/1407.3501/) (2014)
- [What Do We Want From Explainable Artificial Intelligence (XAI)? -- A Stakeholder Perspective on XAI and a Conceptual Model Guiding Interdisciplinary XAI Research](https://mlsanity.com/paper/2102.07817/) (2021)
- [Covariance Matrix Adaptation for the Rapid Illumination of Behavior Space](https://mlsanity.com/paper/1912.02400/) (2019)
- [Using Centroidal Voronoi Tessellations to Scale Up the Multi-dimensional Archive of Phenotypic Elites Algorithm](https://mlsanity.com/paper/1610.05729/) (2016)
- [Neuro-Symbolic Artificial Intelligence: Current Trends](https://mlsanity.com/paper/2105.05330/) (2021)
- [Scaling MAP-Elites to Deep Neuroevolution](https://mlsanity.com/paper/2003.01825/) (2020)
- [Approximating Gradients for Differentiable Quality Diversity in Reinforcement Learning](https://mlsanity.com/paper/2202.03666/) (2022)
- [Discovering Policies with DOMiNO: Diversity Optimization Maintaining Near Optimality](https://mlsanity.com/paper/2205.13521/) (2022)
- [Mapping Hearthstone Deck Spaces through MAP-Elites with Sliding Boundaries](https://mlsanity.com/paper/1904.10656/) (2019)
- [Reviewing the Need for Explainable Artificial Intelligence (xAI)](https://mlsanity.com/paper/2012.01007/) (2020)
- [Talakat: Bullet Hell Generation through Constrained Map-Elites](https://mlsanity.com/paper/1806.04718/) (2018)
- [Neuro-Symbolic AI: An Emerging Class of AI Workloads and their Characterization](https://mlsanity.com/paper/2109.06133/) (2021)
- [Evolutionary learning of interpretable decision trees](https://mlsanity.com/paper/2012.07723/) (2020)
- [Towards Interpretable-AI Policies Induction using Evolutionary Nonlinear Decision Trees for Discrete Action Systems](https://mlsanity.com/paper/2009.09521/) (2020)
- [EVO-RL: Evolutionary-Driven Reinforcement Learning](https://mlsanity.com/paper/2007.04725/) (2020)
- [Interpretable AI for policy-making in pandemics](https://mlsanity.com/paper/2204.04256/) (2022)
- [Qualitative Measurements of Policy Discrepancy for Return-Based Deep Q-Network](https://mlsanity.com/paper/1806.06953/) (2018)
- [Optimisation and Illumination of a Real-world Workforce Scheduling and Routing Application via Map-Elites](https://mlsanity.com/paper/1805.11555/) (2018)
- [Interpretable pipelines with evolutionarily optimized modules for RL tasks with visual inputs](https://mlsanity.com/paper/2202.04943/) (2022)

## Built on by (most cited first, 7 of 7)

- [Bridging Evolutionary Algorithms and Reinforcement Learning: A Comprehensive Survey on Hybrid Algorithms](https://mlsanity.com/paper/2401.11963/) (2024)
- [Q(D)O-ES: Population-based Quality (Diversity) Optimisation for Post Hoc Ensemble Selection in AutoML](https://mlsanity.com/paper/2307.08364/) (2023)
- [From GNNs to Trees: Multi-Granular Interpretability for Graph Neural Networks](https://mlsanity.com/paper/2505.00364/) (2025)
- [Evolutionary Computation and Explainable AI: A Roadmap to Understandable Intelligent Systems](https://mlsanity.com/paper/2406.07811/) (2024)
- [Evo* 2023 -- Late-Breaking Abstracts Volume](https://mlsanity.com/paper/2403.13950/) (2024)
- [Enhance Learning Efficiency of Oblique Decision Tree via Feature Concatenation](https://mlsanity.com/paper/2502.00465/) (2025)
- [BASIL: Best-Action Symbolic Interpretable Learning for Evolving Compact RL Policies](https://mlsanity.com/paper/2506.00328/) (2025)

## Abstract (arXiv)

Addressing the need for explainable Machine Learning has emerged as one of the most important research directions in modern Artificial Intelligence (AI). While the current dominant paradigm in the field is based on black-box models, typically in the form of (deep) neural networks, these models lack direct interpretability for human users, i.e., their outcomes (and, even more so, their inner working) are opaque and hard to understand. This is hindering the adoption of AI in safety-critical applications, where high interests are at stake. In these applications, explainable by design models, such as decision trees, may be more suitable, as they provide interpretability. Recent works have proposed the hybridization of decision trees and Reinforcement Learning, to combine the advantages of the two approaches. So far, however, these works have focused on the optimization of those hybrid models. Here, we apply MAP-Elites for diversifying hybrid models over a feature space that captures both the model complexity and its behavioral variability. We apply our method on two well-known control problems from the OpenAI Gym library, on which we discuss the "illumination" patterns projected by MAP-Elites, comparing its results against existing similar approaches.