# ACTER: Diverse and Actionable Counterfactual Sequences for Explaining and Diagnosing RL Policies

arXiv: https://arxiv.org/abs/2402.06503 · HTML: https://mlsanity.com/paper/2402.06503/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Placed in Interpretable and logic-guided RL, one of 15 directions in Deep reinforcement learning methods.
- Builds on 24 of its 38 references that are in the map.
- First posted on arXiv 9 Feb 2024.

## Placed in

- Deep reinforcement learning methods / [Interpretable and logic-guided RL](https://mlsanity.com/deeprl/interpretable-and-logic-guided-rl/)

## Builds on (most cited first, 24 of 24)

- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Deep Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2002.00444/) (2020)
- [Explaining Machine Learning Classifiers through Diverse Counterfactual Explanations](https://mlsanity.com/paper/1905.07697/) (2019)
- [Deep Reinforcement Learning: An Overview](https://mlsanity.com/paper/1701.07274/) (2017)
- [Metrics for Explainable AI: Challenges and Prospects](https://mlsanity.com/paper/1812.04608/) (2018)
- [Algorithmic Recourse: from Counterfactual Explanations to Interventions](https://mlsanity.com/paper/2002.06278/) (2020)
- [FACE: Feasible and Actionable Counterfactual Explanations](https://mlsanity.com/paper/1909.09369/) (2019)
- [Explainable Reinforcement Learning Through a Causal Lens](https://mlsanity.com/paper/1905.10958/) (2019)
- [Multi-Objective Counterfactual Explanations](https://mlsanity.com/paper/2004.11165/) (2020)
- [Visualizing and Understanding Atari Agents](https://mlsanity.com/paper/1711.00138/) (2017)
- [Explainable Reinforcement Learning: A Survey](https://mlsanity.com/paper/2005.06247/) (2020)
- [Towards Robust and Reliable Algorithmic Recourse](https://mlsanity.com/paper/2102.13620/) (2021)
- [Exploratory Not Explanatory: Counterfactual Analysis of Saliency Maps for Deep Reinforcement Learning](https://mlsanity.com/paper/1912.05743/) (2019)
- [Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations](https://mlsanity.com/paper/1912.09007/) (2019)
- [Explain Your Move: Understanding Agent Actions Using Specific and Relevant Feature Attribution](https://mlsanity.com/paper/1912.12191/) (2019)
- [Counterfactual State Explanations for Reinforcement Learning Agents via Generative Deep Learning](https://mlsanity.com/paper/2101.12446/) (2021)
- [Counterfactual Explanations in Sequential Decision Making Under Uncertainty](https://mlsanity.com/paper/2107.02776/) (2021)
- [What Did You Think Would Happen? Explaining Agent Behaviour Through Intended Outcomes](https://mlsanity.com/paper/2011.05064/) (2020)
- [GANterfactual-RL: Understanding Reinforcement Learning Agents' Strategies through Visual Counterfactual Explanations](https://mlsanity.com/paper/2302.12689/) (2023)
- [Finding Counterfactually Optimal Action Sequences in Continuous State Spaces](https://mlsanity.com/paper/2306.03929/) (2023)
- [Distal Explanations for Model-free Explainable Reinforcement Learning](https://mlsanity.com/paper/2001.10284/) (2020)
- [Visual Explanation using Attention Mechanism in Actor-Critic-based Deep Reinforcement Learning](https://mlsanity.com/paper/2103.04067/) (2021)
- [Learn to Interpret Atari Agents](https://mlsanity.com/paper/1812.11276/) (2018)
- [RACCER: Towards Reachable and Certain Counterfactual Explanations for Reinforcement Learning](https://mlsanity.com/paper/2303.04475/) (2023)

## Built on by (most cited first, 4 of 4)

- [Counterfactual Influence in Markov Decision Processes](https://mlsanity.com/paper/2402.08514/) (2024)
- [Robust Counterfactual Inference in Markov Decision Processes](https://mlsanity.com/paper/2502.13731/) (2025)
- [Semifactual Explanations for Reinforcement Learning](https://mlsanity.com/paper/2409.05435/) (2024)
- [Command-Space Counterfactual Explanations for Pareto-Conditioned Reinforcement Learning](https://mlsanity.com/paper/2608.14963/) (2026)

## Abstract (arXiv)

Understanding how failure occurs and how it can be prevented in reinforcement learning (RL) is necessary to enable debugging, maintain user trust, and develop personalized policies. Counterfactual reasoning has often been used to assign blame and understand failure by searching for the closest possible world in which the failure is avoided. However, current counterfactual state explanations in RL can only explain an outcome using just the current state features and offer no actionable recourse on how a negative outcome could have been prevented. In this work, we propose ACTER (Actionable Counterfactual Sequences for Explaining Reinforcement Learning Outcomes), an algorithm for generating counterfactual sequences that provides actionable advice on how failure can be avoided. ACTER investigates actions leading to a failure and uses the evolutionary algorithm NSGA-II to generate counterfactual sequences of actions that prevent it with minimal changes and high certainty even in stochastic environments. Additionally, ACTER generates a set of multiple diverse counterfactual sequences that enable users to correct failure in the way that best fits their preferences. We also introduce three diversity metrics that can be used for evaluating the diversity of counterfactual sequences. We evaluate ACTER in two RL environments, with both discrete and continuous actions, and show that it can generate actionable and diverse counterfactual sequences. We conduct a user study to explore how explanations generated by ACTER help users identify and correct failure.