# Explainability in reinforcement learning: perspective and position

arXiv: https://arxiv.org/abs/2203.11547 · HTML: https://mlsanity.com/paper/2203.11547/

## Key facts

- Cited by 11 papers in the map (data through 14 Oct 2026).
- Builds on 46 of its 79 references that are in the map.
- First posted on arXiv 22 Mar 2022.

## Builds on (most cited first, 30 of 46)

- [Explainable Artificial Intelligence (XAI): Concepts, Taxonomies, Opportunities and Challenges toward Responsible AI](https://mlsanity.com/paper/1910.10045/) (2019)
- [A Survey Of Methods For Explaining Black Box Models](https://mlsanity.com/paper/1802.01933/) (2018)
- [A Survey on Explainable Artificial Intelligence (XAI): Towards Medical XAI](https://mlsanity.com/paper/1907.07374/) (2019)
- [Explainability in Graph Neural Networks: A Taxonomic Survey](https://mlsanity.com/paper/2012.15445/) (2020)
- [Methods for Interpreting and Understanding Deep Neural Networks](https://mlsanity.com/paper/1706.07979/) (2017)
- [European Union regulations on algorithmic decision-making and a "right to explanation"](https://mlsanity.com/paper/1606.08813/) (2016)
- [Hierarchical Deep Reinforcement Learning: Integrating Temporal Abstraction and Intrinsic Motivation](https://mlsanity.com/paper/1604.06057/) (2016)
- [Opportunities and Challenges in Explainable Artificial Intelligence (XAI): A Survey](https://mlsanity.com/paper/2006.11371/) (2020)
- [Causality for Machine Learning](https://mlsanity.com/paper/1911.10500/) (2019)
- [A Survey on the Explainability of Supervised Machine Learning](https://mlsanity.com/paper/2011.07876/) (2020)
- [Deep Structural Causal Models for Tractable Counterfactual Inference](https://mlsanity.com/paper/2006.06485/) (2020)
- [Programmatically Interpretable Reinforcement Learning](https://mlsanity.com/paper/1804.02477/) (2018)
- [Explainable Reinforcement Learning Through a Causal Lens](https://mlsanity.com/paper/1905.10958/) (2019)
- [Explainable Machine Learning for Scientific Insights and Discoveries](https://mlsanity.com/paper/1905.08883/) (2019)
- [One Explanation Does Not Fit All: A Toolkit and Taxonomy of AI Explainability Techniques](https://mlsanity.com/paper/1909.03012/) (2019)
- [Visualizing and Understanding Atari Agents](https://mlsanity.com/paper/1711.00138/) (2017)
- [Explainable Reinforcement Learning: A Survey](https://mlsanity.com/paper/2005.06247/) (2020)
- [Explainable Deep Learning: A Field Guide for the Uninitiated](https://mlsanity.com/paper/2004.14545/) (2020)
- [Interpretable End-to-end Urban Autonomous Driving with Latent Deep Reinforcement Learning](https://mlsanity.com/paper/2001.08726/) (2020)
- [Explainability Fact Sheets: A Framework for Systematic Assessment of Explainable Approaches](https://mlsanity.com/paper/1912.05100/) (2019)
- [Explainability in Deep Reinforcement Learning](https://mlsanity.com/paper/2008.06693/) (2020)
- [Hierarchical and Interpretable Skill Acquisition in Multi-task Reinforcement Learning](https://mlsanity.com/paper/1712.07294/) (2017)
- [Relational Deep Reinforcement Learning](https://mlsanity.com/paper/1806.01830/) (2018)
- [A Survey on Interpretable Reinforcement Learning](https://mlsanity.com/paper/2112.13112/) (2021)
- [explAIner: A Visual Analytics Framework for Interactive and Explainable Machine Learning](https://mlsanity.com/paper/1908.00087/) (2019)
- [Graying the black box: Understanding DQNs](https://mlsanity.com/paper/1602.02658/) (2016)
- [Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees](https://mlsanity.com/paper/1807.05887/) (2018)
- [Interestingness Elements for Explainable Reinforcement Learning: Understanding Agents' Capabilities and Limitations](https://mlsanity.com/paper/1912.09007/) (2019)
- [Contrastive Explanations for Reinforcement Learning in terms of Expected Consequences](https://mlsanity.com/paper/1807.08706/) (2018)
- [Order in the Court: Explainable AI Methods Prone to Disagreement](https://mlsanity.com/paper/2105.03287/) (2021)

## Built on by (most cited first, 11 of 11)

- [Explainable Artificial Intelligence (XAI) 2.0: A Manifesto of Open Challenges and Interdisciplinary Research Directions](https://mlsanity.com/paper/2310.19775/) (2023)
- [Bridging the Human-AI Knowledge Gap: Concept Discovery and Transfer in AlphaZero](https://mlsanity.com/paper/2310.16410/) (2023)
- [Multi-Agent Reinforcement Learning for Autonomous Driving: A Survey](https://mlsanity.com/paper/2408.09675/) (2024)
- [Interpretable Concept Bottlenecks to Align Reinforcement Learning Agents](https://mlsanity.com/paper/2401.05821/) (2024)
- [Safe and Robust Reinforcement Learning: Principles and Practice](https://mlsanity.com/paper/2403.18539/) (2024)
- [Interpretable end-to-end Neurosymbolic Reinforcement Learning agents](https://mlsanity.com/paper/2410.14371/) (2024)
- [Artificial Collective Intelligence Engineering: a Survey of Concepts and Perspectives](https://mlsanity.com/paper/2304.05147/) (2023)
- [Leveraging Reward Consistency for Interpretable Feature Discovery in Reinforcement Learning](https://mlsanity.com/paper/2309.01458/) (2023)
- [Prismal view of ethics](https://mlsanity.com/paper/2205.13370/) (2022)
- [On Multi-Agent Deep Deterministic Policy Gradients and their Explainability for SMARTS Environment](https://mlsanity.com/paper/2301.09420/) (2023)
- [Explaining Strategic Decisions in Multi-Agent Reinforcement Learning for Aerial Combat Tactics](https://mlsanity.com/paper/2505.11311/) (2025)

## Abstract (arXiv)

Artificial intelligence (AI) has been embedded into many aspects of people's daily lives and it has become normal for people to have AI make decisions for them. Reinforcement learning (RL) models increase the space of solvable problems with respect to other machine learning paradigms. Some of the most interesting applications are in situations with non-differentiable expected reward function, operating in unknown or underdefined environment, as well as for algorithmic discovery that surpasses performance of any teacher, whereby agent learns from experimental experience through simple feedback. The range of applications and their social impact is vast, just to name a few: genomics, game-playing (chess, Go, etc.), general optimization, financial investment, governmental policies, self-driving cars, recommendation systems, etc. It is therefore essential to improve the trust and transparency of RL-based systems through explanations. Most articles dealing with explainability in artificial intelligence provide methods that concern supervised learning and there are very few articles dealing with this in the area of RL. The reasons for this are the credit assignment problem, delayed rewards, and the inability to assume that data is independently and identically distributed (i.i.d.). This position paper attempts to give a systematic overview of existing methods in the explainable RL area and propose a novel unified taxonomy, building and expanding on the existing ones. The position section describes pragmatic aspects of how explainability can be observed. The gap between the parties receiving and generating the explanation is especially emphasized. To reduce the gap and achieve honesty and truthfulness of explanations, we set up three pillars: proactivity, risk attitudes, and epistemological constraints. To this end, we illustrate our proposal on simple variants of the shortest path problem.