中文
相关论文

相关论文: Interpretable and Explainable Logical Policies via…

200 篇论文

Deep Reinforcement Learning uses a deep neural network to encode a policy, which achieves very good performance in a wide range of applications but is widely regarded as a black box model. A more interpretable alternative to deep networks…

机器学习 · 计算机科学 2022-09-09 Arne Gevaert , Jonathan Peck , Yvan Saeys

Multi-agent robotic systems are increasingly operating in real-world environments in close proximity to humans, yet are largely controlled by policy models with inscrutable deep neural network representations. We introduce a method for…

机器学习 · 计算机科学 2023-02-24 Renos Zabounidis , Joseph Campbell , Simon Stepputtis , Dana Hughes , Katia Sycara

Recent work on neuro-symbolic inductive logic programming has led to promising approaches that can learn explanatory rules from noisy, real-world data. While some proposals approximate logical operators with differentiable operators from…

人工智能 · 计算机科学 2021-12-08 Prithviraj Sen , Breno W. S. R. de Carvalho , Ryan Riegel , Alexander Gray

Deep reinforcement learning (RL) has recently led to many breakthroughs on a range of complex control tasks. However, the agent's decision-making process is generally not transparent. The lack of interpretability hinders the applicability…

计算机视觉与模式识别 · 计算机科学 2021-03-22 Wenjie Shi , Gao Huang , Shiji Song , Zhuoyuan Wang , Tingyu Lin , Cheng Wu

Semantic interpretability in Reinforcement Learning (RL) enables transparency and verifiability of decision-making. Achieving semantic interpretability in reinforcement learning requires (1) a feature space composed of human-understandable…

人工智能 · 计算机科学 2025-11-03 Zhaoxin Li , Zhang Xi-Jia , Batuhan Altundas , Letian Chen , Rohan Paleja , Matthew Gombolay

Natural language serves as the primary mode of communication when an intelligent agent with a physical presence engages with human beings. While a plethora of research focuses on natural language understanding (NLU), encompassing endeavors…

机器人学 · 计算机科学 2023-10-25 Chayan Sarkar , Avik Mitra , Pradip Pramanick , Tapas Nayak

The success of neural networks comes hand in hand with a desire for more interpretability. We focus on text classifiers and make them more interpretable by having them provide a justification, a rationale, for their predictions. We approach…

计算与语言 · 计算机科学 2020-06-22 Jasmijn Bastings , Wilker Aziz , Ivan Titov

We present Revel, a partially neural reinforcement learning (RL) framework for provably safe exploration in continuous state and action spaces. A key challenge for provably safe deep RL is that repeatedly verifying neural networks within a…

机器学习 · 计算机科学 2020-10-27 Greg Anderson , Abhinav Verma , Isil Dillig , Swarat Chaudhuri

We introduce the Rule Network with Selective Logical Operators (RNS), a novel neural architecture that employs \textbf{selective logical operators} to adaptively choose between AND and OR operations at each neuron during training. Unlike…

机器学习 · 计算机科学 2026-04-03 Bowen Wei , Ziwei Zhu

The capability of making interpretable and self-explanatory decisions is essential for developing responsible machine learning systems. In this work, we study the learning to explain problem in the scope of inductive logic programming…

人工智能 · 计算机科学 2020-02-20 Yuan Yang , Le Song

Artificial Neural Networks are powerful function approximators capable of modelling solutions to a wide variety of problems, both supervised and unsupervised. As their size and expressivity increases, so too does the variance of the model,…

神经与进化计算 · 计算机科学 2018-01-26 Richard Evans , Edward Grefenstette

Deep reinforcement learning (RL) agents rely on shortcut learning, preventing them from generalizing to slightly different environments. To address this problem, symbolic method, that use object-centric states, have been developed. However,…

人工智能 · 计算机科学 2025-11-04 Nils Grandien , Quentin Delfosse , Kristian Kersting

Text-based games (TBGs) have emerged as an important collection of NLP tasks, requiring reinforcement learning (RL) agents to combine natural language understanding with reasoning. A key challenge for agents attempting to solve such tasks…

计算与语言 · 计算机科学 2024-03-19 Kinjal Basu , Keerthiram Murugesan , Subhajit Chaudhury , Murray Campbell , Kartik Talamadupula , Tim Klinger

In the field of high-performance computing (HPC), there has been recent exploration into the use of deep reinforcement learning for cluster scheduling (DRL scheduling), which has demonstrated promising outcomes. However, a significant…

机器学习 · 计算机科学 2024-03-26 Boyang Li , Zhiling Lan , Michael E. Papka

Deep reinforcement learning (DRL) has gained great success by learning directly from high-dimensional sensory inputs, yet is notorious for the lack of interpretability. Interpretability of the subtasks is critical in hierarchical…

人工智能 · 计算机科学 2019-03-01 Daoming Lyu , Fangkai Yang , Bo Liu , Steven Gustafson

Natural and formal languages provide an effective mechanism for humans to specify instructions and reward functions. We investigate how to generate policies via RL when reward functions are specified in a symbolic language captured by…

Recently, deep reinforcement learning (DRL) methods have achieved impressive performance on tasks in a variety of domains. However, neural network policies produced with DRL methods are not human-interpretable and often have difficulty…

机器学习 · 计算机科学 2022-02-02 Dweep Trivedi , Jesse Zhang , Shao-Hua Sun , Joseph J. Lim

Rule-based models, e.g., decision trees, are widely used in scenarios demanding high model interpretability for their transparent inner structures and good model expressivity. However, rule-based models are hard to optimize, especially on…

机器学习 · 计算机科学 2024-01-31 Zhuo Wang , Wei Zhang , Ning Liu , Jianyong Wang

Modern vision-language models (VLMs) deliver impressive predictive accuracy yet offer little insight into 'why' a decision is reached, frequently hallucinating facts, particularly when encountering out-of-distribution data. Neurosymbolic…

计算机视觉与模式识别 · 计算机科学 2025-11-18 Sanchit Sinha , Guangzhi Xiong , Zhenghao He , Aidong Zhang

Rule-based models offer interpretability but struggle with complex data, while deep neural networks excel in performance yet lack transparency. This work investigates a neuro-symbolic rule learning neural network named RL-Net that learns…

机器学习 · 计算机科学 2025-07-01 Sarah Seifi , Tobias Sukianto , Cecilia Carbonelli , Lorenzo Servadei , Robert Wille