Explainable Reinforcement Learning

Explainable Reinforcement Learning (XRL) aims to make the decision-making processes of reinforcement learning (RL) agents more transparent and understandable. Current research focuses on developing methods that provide both local (explaining single actions) and global (explaining overall behavior) explanations, often employing techniques like reward decomposition, counterfactual analysis, and interpretable model architectures such as decision trees. This work is crucial for building trust in RL systems, particularly in high-stakes applications like healthcare and finance, and for facilitating debugging and improved human-agent collaboration.

Papers

November 23, 2022

Introspection-based Explainable Reinforcement Learning in Episodic and Non-episodic Scenarios
Niclas Schroeter, Francisco Cruz, Stefan Wermter
Episodic Reinforcement Learning Explainable Reinforcement Learning Uncertain Episode Length

November 12, 2022

A Survey on Explainable Reinforcement Learning: Concepts, Algorithms, Challenges
Yunpeng Qing, Shunyu Liu, Jie Song, Huiqiong Wang, Mingli Song
Reinforcement Learning Timely Survey Deep Reinforcement Learning Technical Challenge Practical Algorithm Concept Identification Explainable Reinforcement Learning Post Hoc Explainability

October 12, 2022

Explaining Online Reinforcement Learning Decisions of Self-Adaptive Systems
Felix Feit, Andreas Metzger, Klaus Pohl
Reinforcement Learning Online Reinforcement Learning Explainable Reinforcement Learning Self Adaptive System

September 24, 2022

Explainable Reinforcement Learning via Model Transforms
Mira Finkelstein, Lucy Liu, Nitsan Levy Schlot, Yoav Kolumbus, David C. Parkes, Jeffrey S. Rosenshein, Sarah Keren
Reinforcement Learning Markov Decision Process High Explainability Agent Behavior Emergent Behavior Explainable Reinforcement Learning Model Transformation

August 18, 2022

Explainable Reinforcement Learning on Financial Stock Trading using SHAP
Satyam Kumar, Mendhikar Vishal, Vadlamani Ravi
Artificial Intelligence Explainable Artificial Intelligence Shapley Additive Explanation Explainable Reinforcement Learning

April 26, 2022

Toward Policy Explanations for Multi-Agent Reinforcement Learning
Kayla Boggess, Sarit Kraus, Lu Feng
Multi Agent Reinforcement Learning Multi Agent Agent Behavior Explainable Reinforcement Learning Cooperative Agent Interpretable Policy

March 22, 2022

Explainability in reinforcement learning: perspective and position
Agneza Krajna, Mario Brcic, Tomislav Lipic, Juraj Doncevic
Reinforcement Learning Artificial Intelligence High Explainability Visual Perspective Product Specific Position Information Explainable Reinforcement Learning Artificial Intelligence Method

March 21, 2022

ReCCoVER: Detecting Causal Confusion for Explainable Reinforcement Learning
Jasmina Gajcin, Ivana Dusparic
Deep Reinforcement Learning State Space Spurious Correlation Total Correlation Explainable Reinforcement Learning

February 17, 2022

A Survey of Explainable Reinforcement Learning
Stephanie Milani, Nicholay Topin, Manuela Veloso, Fei Fang
Timely Survey Explainable Machine Learning Human Like RL Explainable Reinforcement Learning

December 16, 2021

Inherently Explainable Reinforcement Learning in Natural Language
Xiangyu Peng, Mark O. Riedl, Prithviraj Ammanabrolu
Natural Language High Explainability Reinforcement Learning Agent Local Explanation Explainable Reinforcement Learning Text Based Game Environment

November 26, 2021

Reinforcement Explanation Learning
Siddhant Agarwal, Owais Iqbal, Sree Aditya Buridi, Madda Manjusha, Abir Das
Reinforcement Learning Black Box Saliency Map Explainable Reinforcement Learning Saliency Map Generation