Interpretable Policy

Interpretable policy research focuses on developing machine learning models whose decision-making processes are transparent and understandable, addressing the "black box" problem of many AI systems. Current research emphasizes tree-based models, including decision trees and variations like Optimal MDP Decision Trees and Interpretable Continuous Control Trees, as well as neuro-symbolic approaches that combine neural networks with symbolic reasoning to create more explainable policies. This work is crucial for building trust in AI systems, particularly in high-stakes applications like autonomous driving and healthcare, where understanding the reasoning behind decisions is paramount for safety and accountability.

Papers

August 15, 2024

$EvoAl^{2048}$
Bernhard J. Berger (1 and 2), Christina Plump (3), Rolf Drechsler (4 and 3) ((1) University of Rostock, Software Engineering Chair Rostock, Germany, (2) Hamburg University of Technology, Institute of Embedded Systems, Germany, (3) DFKI - Cyber-Physical Systems Bremen, Germany, (4) University of Bremen, Departments of Mathematics and Computer Science)
AI System Policy Design Model Based Optimization Interpretable Policy Interpretable Control

May 30, 2024

Policy Trees for Prediction: Interpretable and Adaptive Model Selection for Machine Learning
Dimitris Bertsimas, Matthew Peroni
Machine Learning Human Prediction Interpretable Model Interpretable Policy Adaptive Linear Decision Tree Policy

May 23, 2024

Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning
Hector Kohler, Quentin Delfosse, Riad Akrour, Kristian Kersting, Philippe Preux
Reinforcement Learning Inherent Interpretability Interpretable Way Interpretable Policy Differentiable Tree Programmatic Policy

April 16, 2024

Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop
Hector Kohler, Quentin Delfosse, Paul Festor, Philippe Preux
Reinforcement Learning Explainable Reinforcement Learning Research Community Interpretable Policy Reinforcement Learning Paradigm

February 14, 2024

Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning
Michael Lanier, Ying Xu, Nathan Jacobs, Chongjie Zhang, Yevgeniy Vorobeychik
Deep Reinforcement Learning Partially Observable Markov Decision Process Observable Environment Interpretable Policy Supervised Reinforcement Learning

November 16, 2023

Interpretable Reinforcement Learning for Robotics and Continuous Control
Rohan Paleja, Letian Chen, Yaru Niu, Andrew Silva, Zhaoxin Li, Songan Zhang, Chace Ritchie, Sugju Choi, Kimberlee Chestnut Chang, Hongtei Eric Tseng, Yan Wang, Subramanya Nageshrao, Matthew Gombolay
Reinforcement Learning Robotics Domain Continuous Control Driving Scenario Interpretable Policy

June 2, 2023

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction
Quentin Delfosse, Hikaru Shindo, Devendra Dhami, Kristian Kersting
Reinforcement Learning Interpretable Way Policy Design Differentiable Logic Interpretable Policy

May 12, 2023

S-REINFORCE: A Neuro-Symbolic Policy Gradient Approach for Interpretable Reinforcement Learning
Rajdeep Dutta, Qincheng Wang, Ankur Singh, Dhruv Kumarjiguda, Li Xiaoli, Senthilnath Jayavelu
Reinforcement Learning Policy Gradient Dynamic Decision Interpretable Policy Symbolic Policy

January 30, 2023

Optimal Decision Tree Policies for Markov Decision Processes
Daniël Vos, Sicco Verwer
Markov Decision Process Decision Tree Interpretable Policy Decision Tree Policy

July 20, 2022

Constrained Prescriptive Trees via Column Generation
Shivaram Subramanian, Wei Sun, Youssef Drissi, Markus Ettl
Constrained Policy Optimization Column Generation Interpretable Policy Informed Decision Prescriptive Analytics

May 2, 2022

Using Constraint Programming and Graph Representation Learning for Generating Interpretable Cloud Security Policies
Mikhail Kazdagli, Mohit Tiwari, Akshat Kumar
Graph Representation Learning Cloud Computing Constraint Programming Interpretable Policy Secure Cloud

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

April 8, 2022

Interpretable AI for policy-making in pandemics
Leonardo Lucio Custode, Giovanni Iacca
Reinforcement Learning Evolutionary Computation Global Pandemic Interpretable AI Interpretable Policy Policy Making

February 4, 2022

Learning Interpretable, High-Performing Policies for Autonomous Driving
Rohan Paleja, Yaru Niu, Andrew Silva, Chace Ritchie, Sugju Choi, Matthew Gombolay
Autonomous Driving Autonomous Vehicle Interpretable Policy Interpretable Learning High Performing Policy

January 25, 2022

Learning Resource Allocation Policies from Observational Data with an Application to Homeless Services Delivery
Aida Rahmattalabi, Phebe Vayanos, Kathryn Dullerud, Eric Rice
Application Proficiency Causal Inference Resource Allocation Mixed Integer Fairness Constraint Observational Data Interpretable Policy

January 18, 2022

Programmatic Policy Extraction by Iterative Local Search
Rasmus Larsen, Mikkel Nørgaard Schmidt
Local Search Interpretable Policy

January 15, 2022

Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection
Yuefei Lyu, Xiaoyu Yang, Jiaxin Liu, Philip S. Yu, Sihong Xie, Xi Zhang
Reinforcement Learning Policy OpTimization Interpretable Way Rumor Detection Model Attack Interpretable Policy Effective Reinforcement Learning

Interpretable Policy

Papers

$EvoAl^{2048}$

Policy Trees for Prediction: Interpretable and Adaptive Model Selection for Machine Learning

Interpretable and Editable Programmatic Tree Policies for Reinforcement Learning

Towards a Research Community in Interpretable Reinforcement Learning: the InterpPol Workshop

Learning Interpretable Policies in Hindsight-Observable POMDPs through Partially Supervised Reinforcement Learning

Interpretable Reinforcement Learning for Robotics and Continuous Control

Interpretable and Explainable Logical Policies via Neurally Guided Symbolic Abstraction

S-REINFORCE: A Neuro-Symbolic Policy Gradient Approach for Interpretable Reinforcement Learning

Optimal Decision Tree Policies for Markov Decision Processes

Constrained Prescriptive Trees via Column Generation

Using Constraint Programming and Graph Representation Learning for Generating Interpretable Cloud Security Policies

Toward Policy Explanations for Multi-Agent Reinforcement Learning

Interpretable AI for policy-making in pandemics

Learning Interpretable, High-Performing Policies for Autonomous Driving

Learning Resource Allocation Policies from Observational Data with an Application to Homeless Services Delivery

Programmatic Policy Extraction by Iterative Local Search

Interpretable and Effective Reinforcement Learning for Attacking against Graph-based Rumor Detection