Compositional Concept-Based Neuron-Level Explanations for Deep Reinforcement Learning
- 30 June 2026
- book chapter
- Published by Springer Nature
- p. 52-64
Abstract
No abstract availableAll Related Versions
This publication has 12 references indexed in Scilit:
- Explainable Reinforcement Learning via a Causal World Model2023
- Global Concept-Based Interpretability for Graph Neural Networks via Neuron AnalysisProceedings of the AAAI Conference on Artificial Intelligence, 2023
- Explainable Deep Reinforcement Learning: State of the Art and ChallengesACM Computing Surveys, 2022
- Free-Lunch Saliency via Attention in Atari Agents2019
- Reinforcement Learning with Explainability for Traffic Signal Control2019
- Visualization of Deep Reinforcement Learning using Grad-CAM: How AI Plays Atari Games?2019
- Toward Interpretable Deep Reinforcement Learning with Linear Model U-Trees2019
- Network Dissection: Quantifying Interpretability of Deep Visual Representations2017
- Improving Robot Controller Transparency Through Autonomous Policy Explanation2017
- Who Belongs in the Family?Psychometrika, 1953