paper-with-me

홈 › Papers

Contrastive Explanations for Reinforcement Learning via Embedded Self Predictions

2020-10-11 · ICLR 2021 1 · Zhengxian Lin, Kim-Ho Lam, Alan Fern

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.

📄 PDF Abstract BibTeX arXiv:2010.05180

Code (1)

SuerpX/Embedded-Self-Predictions 공식 구현 pytorch

Tasks

Deep Reinforcement Learningreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Methods 이 논문이 사용한 방법론

Hierarchical Feature Fusion Hierarchical Feature Fusion (HFF) is a feature fusion method employed in ESP and EESP image…
Dilated Convolution 설명 없음
Pointwise Convolution Pointwise Convolution is a type of convolution that uses a 1x1 kernel: a kernel that iterates through every single point. This…
ESP 설명 없음

Similar Papers 제목 키워드 기반

(When) Are Contrastive Explanations of Reinforcement Learning Helpful?

2022-11-14 · Sanjana Narayanan, Isaac Lage, Finale Doshi-Velez

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

2024-07-16 · Zhenhua Huang, Kunhao Li, Shaojie Wang, Zhaohong Jia 외

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 NetworkTriplet

The Blessing of Reasoning: LLM-Based Contrastive Explanations in Black-Box Recommender Systems

2025-02-24 · Yuyan Wang, Pan Li, Minmin Chen

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 Systems

Concept-Based Abductive and Contrastive Explanations for Behaviors of Vision Models

2026-05-07 · Ronaldo Canizales, Divya Gopinath, Corina Păsăreanu, Ravi Mangal arxiv

*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

2018-05-27 · Freddy Lecue, Jiewen Wu

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