paper-with-me

Papers

Interpretable Model-based Hierarchical Reinforcement Learning using Inductive Logic Programming

2021-06-21 · Duo Xu, Faramarz Fekri

Recently deep reinforcement learning has achieved tremendous success in wide ranges of applications. However, it notoriously lacks data-efficiency and interpretability. Data-efficiency is important as interacting with the environment is expensive. Further, interpretability can increase the transparency of the black-box-style deep RL models and hence gain trust from the users. In this work, we propose a new hierarchical framework via symbolic RL, leveraging a symbolic transition model to improve the data-efficiency and introduce the interpretability for learned policy. This framework consists of a high-level agent, a subtask solver and a symbolic transition model. Without assuming any prior knowledge on the state transition, we adopt inductive logic programming (ILP) to learn the rules of symbolic state transitions, introducing interpretability and making the learned behavior understandable to users. In empirical experiments, we confirmed that the proposed framework offers approximately between 30\% to 40\% more data efficiency over previous methods.

📄 PDF Abstract BibTeX arXiv:2106.11417

Code (0)

등록된 구현이 없습니다.

Tasks

Deep Reinforcement LearningHierarchical Reinforcement LearningInductive logic programmingreinforcement-learningReinforcement LearningReinforcement Learning (RL)

Similar Papers 제목 키워드 기반

Neuro-Symbolic Hierarchical Rule Induction

2021-12-26 · Claire Glanois, Xuening Feng, Zhaohui Jiang, Paul Weng 외

We propose an efficient interpretable neuro-symbolic model to solve Inductive Logic Programming (ILP) problems. In this model, which is built from a set of meta-rules organised in a hierarchical structure, first-order ru…

Inductive logic programmingreinforcement-learningReinforcement Learning (RL)

Deep Inductive Logic Programming meets Reinforcement Learning

2023-08-30 · Andreas Bueff, Vaishak Belle

One approach to explaining the hierarchical levels of understanding within a machine learning model is the symbolic method of inductive logic programming (ILP), which is data efficient and capable of learning first-order…

Inductive logic programmingreinforcement-learningReinforcement Learning

Neural Logic Reinforcement Learning

2019-04-24 · Zhengyao Jiang, Shan Luo

Deep reinforcement learning (DRL) has achieved significant breakthroughs in various tasks. However, most DRL algorithms suffer a problem of generalizing the learned policy which makes the learning performance largely aff…

Deep Reinforcement LearningInductive logic programmingPolicy Gradient Methodsreinforcement-learning+2

Learn to Explain Efficiently via Neural Logic Inductive Learning

2019-10-06 · ICLR 2020 1 · Yuan Yang, Le Song

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 log…

Inductive LearningInductive logic programming

Learning Compositional Symbolic Task Rules from Demonstrations with Inductive Logic Programming

2026-05-26 · Oleh Borys, Karla Stepanova arxiv

Learning from Demonstration~(LfD) should capture not only how a task is executed, but also its high-level task structure that explains the demonstrated behavior. As robots become more autonomous, such task representation…

Inductive logic programming