Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions
We investigate a deep reinforcement learning (RL) architecture that supports explaining why a learned agent prefers one action over another. The key idea is to learn action-values that are directly represented via human-understandable properties of expected futures. This is realized via the embedded self-prediction (ESP)model, which learns said properties in terms of human provided features. Action preferences can then be explained by contrasting the future properties predicted for each action. To address cases where there are a large number of features, we develop a novel method for computing minimal sufficient explanations from anESP. Our case studies in three domains, including a complex strategy game, show that ESP models can be effectively learned and support insightful explanations.
Code (1)
Tasks
Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)Methods 이 논문이 사용한 방법론
Similar Papers 제목 키워드 기반
(When) Are Contrastive Explanations of Reinforcement Learning Helpful?
Global explanations of a reinforcement learning (RL) agent's expected behavior can make it safer to deploy. However, such explanations are often difficult to understand because of the complicated nature of many RL polici…
reinforcement-learningReinforcement LearningReinforcement Learning (RL)SES: Bridging the Gap Between Explainability and Prediction of Graph Neural Networks
Despite the Graph Neural Networks' (GNNs) proficiency in analyzing graph data, achieving high-accuracy and interpretable predictions remains challenging. Existing GNN interpreters typically provide post-hoc explanations …
Contrastive LearningGraph Neural NetworkTripletThe Blessing of Reasoning: LLM-Based Contrastive Explanations in Black-Box Recommender Systems
Modern recommender systems use ML models to predict consumer preferences from consumption history. Although these "black-box" models achieve impressive predictive performance, they often suffer from a lack of transparenc…
Learning TheoryRecommendation SystemsConcept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models
*Concept-based explanations* offer a promising approach for explaining the predictions of deep neural networks in terms of high-level, human-understandable concepts. However, existing methods either do not establish a ca…
Semantic Explanations of Predictions
The main objective of explanations is to transmit knowledge to humans. This work proposes to construct informative explanations for predictions made from machine learning models. Motivated by the observations from social…
General Classification