# Model-agnostic and Scalable Counterfactual Explanations via Reinforcement Learning

arXiv: https://arxiv.org/abs/2106.02597 · HTML: https://mlsanity.com/paper/2106.02597/

## Key facts

- Cited by 15 papers in the map (data through 14 Oct 2026).
- Builds on 26 of its 41 references that are in the map.
- First posted on arXiv 4 Jun 2021.

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

- [Adam: A Method for Stochastic Optimization](https://mlsanity.com/paper/1412.6980/) (2014)
- [XGBoost: A Scalable Tree Boosting System](https://mlsanity.com/paper/1603.02754/) (2016)
- ["Why Should I Trust You?": Explaining the Predictions of Any Classifier](https://mlsanity.com/paper/1602.04938/) (2016)
- [Deep Learning Face Attributes in the Wild](https://mlsanity.com/paper/1411.7766/) (2014)
- [Continuous control with deep reinforcement learning](https://mlsanity.com/paper/1509.02971/) (2015)
- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [UMAP: Uniform Manifold Approximation and Projection for Dimension Reduction](https://mlsanity.com/paper/1802.03426/) (2018)
- [Conditional Generative Adversarial Nets](https://mlsanity.com/paper/1411.1784/) (2014)
- [Counterfactual Explanations without Opening the Black Box: Automated Decisions and the GDPR](https://mlsanity.com/paper/1711.00399/) (2017)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Explanations based on the Missing: Towards Contrastive Explanations with Pertinent Negatives](https://mlsanity.com/paper/1802.07623/) (2018)
- [Failing Loudly: An Empirical Study of Methods for Detecting Dataset Shift](https://mlsanity.com/paper/1810.11953/) (2018)
- [Interpretable Counterfactual Explanations Guided by Prototypes](https://mlsanity.com/paper/1907.02584/) (2019)
- [The What-If Tool: Interactive Probing of Machine Learning Models](https://mlsanity.com/paper/1907.04135/) (2019)
- [Local Rule-Based Explanations of Black Box Decision Systems](https://mlsanity.com/paper/1805.10820/) (2018)
- [Preserving Causal Constraints in Counterfactual Explanations for Machine Learning Classifiers](https://mlsanity.com/paper/1912.03277/) (2019)
- [Towards Realistic Individual Recourse and Actionable Explanations in Black-Box Decision Making Systems](https://mlsanity.com/paper/1907.09615/) (2019)
- [A survey of algorithmic recourse: definitions, formulations, solutions, and prospects](https://mlsanity.com/paper/2010.04050/) (2020)
- [Inverse Classification for Comparison-based Interpretability in Machine Learning](https://mlsanity.com/paper/1712.08443/) (2017)
- [Measurable Counterfactual Local Explanations for Any Classifier](https://mlsanity.com/paper/1908.03020/) (2019)
- [DECE: Decision Explorer with Counterfactual Explanations for Machine Learning Models](https://mlsanity.com/paper/2008.08353/) (2020)
- [Generative Counterfactual Introspection for Explainable Deep Learning](https://mlsanity.com/paper/1907.03077/) (2019)
- [CERTIFAI: Counterfactual Explanations for Robustness, Transparency, Interpretability, and Fairness of Artificial Intelligence models](https://mlsanity.com/paper/1905.07857/) (2019)
- [Conditional Generative Models for Counterfactual Explanations](https://mlsanity.com/paper/2101.10123/) (2021)
- [PermuteAttack: Counterfactual Explanation of Machine Learning Credit Scorecards](https://mlsanity.com/paper/2008.10138/) (2020)
- [Born Identity Network: Multi-way Counterfactual Map Generation to Explain a Classifier's Decision](https://mlsanity.com/paper/2011.10381/) (2020)

## Built on by (most cited first, 15 of 15)

- [Redefining Counterfactual Explanations for Reinforcement Learning: Overview, Challenges and Opportunities](https://mlsanity.com/paper/2210.11846/) (2022)
- [Achieving Diversity in Counterfactual Explanations: a Review and Discussion](https://mlsanity.com/paper/2305.05840/) (2023)
- [RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning](https://mlsanity.com/paper/2303.04475/) (2023)
- [For Better or Worse: The Impact of Counterfactual Explanations' Directionality on User Behavior in xAI](https://mlsanity.com/paper/2306.07637/) (2023)
- [DiCoFlex: Model-agnostic diverse counterfactuals with flexible control](https://mlsanity.com/paper/2505.23700/) (2025)
- [Counterfactual Maps: What They Are and How to Find Them](https://mlsanity.com/paper/2602.09128/) (2026)
- [Counterfactual Explanation for Regression via Disentanglement in Latent Space](https://mlsanity.com/paper/2311.08228/) (2023)
- [Individualised Counterfactual Examples Using Conformal Prediction Intervals](https://mlsanity.com/paper/2505.22326/) (2025)
- [DISCOVER: A Solver for Distributional Counterfactual Explanations](https://mlsanity.com/paper/2603.16436/) (2026)
- [HEX: Human-in-the-loop Explainability via Deep Reinforcement Learning](https://mlsanity.com/paper/2206.01343/) (2022)
- [Counterfactual Explanation via Search in Gaussian Mixture Distributed Latent Space](https://mlsanity.com/paper/2307.13390/) (2023)
- [No Dtrain: Model-Agnostic Counterfactual Explanations Using Reinforcement Learning](https://mlsanity.com/paper/2405.18563/) (2024)
- [The Impact of Machine Learning Uncertainty on the Robustness of Counterfactual Explanations](https://mlsanity.com/paper/2602.00063/) (2026)
- [RecourseBench: A Modular Framework for Reproducible Algorithmic Recourse Evaluation](https://mlsanity.com/paper/2606.16113/) (2026)
- [Class-Aware Reinforcement Learning for Counterfactual Explanation Generation](https://mlsanity.com/paper/2607.27905/) (2026)

## Abstract (arXiv)

Counterfactual instances are a powerful tool to obtain valuable insights into automated decision processes, describing the necessary minimal changes in the input space to alter the prediction towards a desired target. Most previous approaches require a separate, computationally expensive optimization procedure per instance, making them impractical for both large amounts of data and high-dimensional data. Moreover, these methods are often restricted to certain subclasses of machine learning models (e.g. differentiable or tree-based models). In this work, we propose a deep reinforcement learning approach that transforms the optimization procedure into an end-to-end learnable process, allowing us to generate batches of counterfactual instances in a single forward pass. Our experiments on real-world data show that our method i) is model-agnostic (does not assume differentiability), relying only on feedback from model predictions; ii) allows for generating target-conditional counterfactual instances; iii) allows for flexible feature range constraints for numerical and categorical attributes, including the immutability of protected features (e.g. gender, race); iv) is easily extended to other data modalities such as images.