A Review of Validation and Verification of Neural Network-based Policies for Sequential Decision Making

• URL: http://arxiv.org/abs/2312.09680v1
• Date: Fri, 15 Dec 2023 10:52:42 GMT
• Title: A Review of Validation and Verification of Neural Network-based Policies for Sequential Decision Making
• Authors: Q. Mazouni, H. Spieker, A. Gotlieb and M. Acher
• Abstract summary: In sequential decision making, neural networks (NNs) are nowadays commonly used to represent and learn the agent's policy. Novel approaches have emerged to adapt those techniques to NN-based policies for sequential decision making.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: In sequential decision making, neural networks (NNs) are nowadays commonly used to represent and learn the agent's policy. This area of application has implied new software quality assessment challenges that traditional validation and verification practises are not able to handle. Subsequently, novel approaches have emerged to adapt those techniques to NN-based policies for sequential decision making. This survey paper aims at summarising these novel contributions and proposing future research directions. We conducted a literature review of recent research papers (from 2018 to beginning of 2023), whose topics cover aspects of the test or verification of NN-based policies. The selection has been enriched by a snowballing process from the previously selected papers, in order to relax the scope of the study and provide the reader with insight into similar verification challenges and their recent solutions. 18 papers have been finally selected. Our results show evidence of increasing interest for this subject. They highlight the diversity of both the exact problems considered and the techniques used to tackle them.

Related papers

• A Comprehensive Survey on Legal Summarization: Challenges and Future Directions [12.03238629982852]
  We thoroughly review over 120 papers spanning the modern transformer' era of natural language processing (NLP) We present existing research along several axes and discuss trends, challenges, and opportunities for future research.
  arXiv  Detail & Related papers  (2025-01-29T18:22:14Z)
• A Survey on Neural Question Generation: Methods, Applications, and Prospects [56.97451350691765]
  The survey begins with an overview of NQG's background, encompassing the task's problem formulation. It then methodically classifies NQG approaches into three predominant categories: structured NQG, unstructured NQG, and hybrid NQG. The survey culminates with a forward-looking perspective on the trajectory of NQG, identifying emergent research trends and prospective developmental paths.
  arXiv  Detail & Related papers  (2024-02-28T11:57:12Z)
• Fact-checking based fake news detection: a review [27.016249665465544]
  The paper systematically explains the task definition and core problems of fact-based fake news detection. The paper summarizes the existing detection methods based on the algorithm principles.
  arXiv  Detail & Related papers  (2024-01-03T12:47:02Z)
• A Comprehensive Survey on Relation Extraction: Recent Advances and New Frontiers [76.51245425667845]
  Relation extraction (RE) involves identifying the relations between entities from underlying content. Deep neural networks have dominated the field of RE and made noticeable progress. This survey is expected to facilitate researchers' collaborative efforts to address the challenges of real-world RE systems.
  arXiv  Detail & Related papers  (2023-06-03T08:39:25Z)
• Backward Reachability Analysis of Neural Feedback Loops: Techniques for Linear and Nonlinear Systems [59.57462129637796]
  This paper presents a backward reachability approach for safety verification of closed-loop systems with neural networks (NNs) The presence of NNs in the feedback loop presents a unique set of problems due to the nonlinearities in their activation functions and because NN models are generally not invertible. We present frameworks for calculating BP over-approximations for both linear and nonlinear systems with control policies represented by feedforward NNs.
  arXiv  Detail & Related papers  (2022-09-28T13:17:28Z)
• A Survey of Neural Trees [34.073451014924345]
  Neural networks (NNs) and decision trees (DTs) are both popular models of machine learning. To bring the best of the two worlds, a variety of approaches are proposed to integrate NNs and DTs explicitly or implicitly. This survey aims to present a comprehensive review of NTs and attempts to identify how they enhance the model interpretability.
  arXiv  Detail & Related papers  (2022-09-07T18:33:45Z)
• Recent Few-Shot Object Detection Algorithms: A Survey with Performance Comparison [54.357707168883024]
  Few-Shot Object Detection (FSOD) mimics the humans' ability of learning to learn. FSOD intelligently transfers the learned generic object knowledge from the common heavy-tailed, to the novel long-tailed object classes. We give an overview of FSOD, including the problem definition, common datasets, and evaluation protocols.
  arXiv  Detail & Related papers  (2022-03-27T04:11:28Z)
• A Systematic Review on the Detection of Fake News Articles [0.0]
  It has been argued that fake news and the spread of false information pose a threat to societies throughout the world. To combat this threat, a number of Natural Language Processing (NLP) approaches have been developed. This paper aims to delineate the approaches for fake news detection that are most performant, identify limitations with existing approaches, and suggest ways these can be mitigated.
  arXiv  Detail & Related papers  (2021-10-18T21:29:11Z)
• A Review of Uncertainty Quantification in Deep Learning: Techniques, Applications and Challenges [76.20963684020145]
  Uncertainty quantification (UQ) plays a pivotal role in reduction of uncertainties during both optimization and decision making processes. Bizarre approximation and ensemble learning techniques are two most widely-used UQ methods in the literature. This study reviews recent advances in UQ methods used in deep learning and investigates the application of these methods in reinforcement learning.
  arXiv  Detail & Related papers  (2020-11-12T06:41:05Z)
• A Survey of Active Learning for Text Classification using Deep Neural Networks [1.2310316230437004]
  Natural language processing (NLP) and neural networks (NNs) have both undergone significant changes in recent years. For active learning (AL) purposes, NNs are, however, less commonly used -- despite their current popularity.
  arXiv  Detail & Related papers  (2020-08-17T12:53:20Z)
• Novel Policy Seeking with Constrained Optimization [131.67409598529287]
  We propose to rethink the problem of generating novel policies in reinforcement learning tasks. We first introduce a new metric to evaluate the difference between policies and then design two practical novel policy generation methods. The two proposed methods, namely the Constrained Task Novel Bisector (CTNB) and the Interior Policy Differentiation (IPD), are derived from the feasible direction method and the interior point method commonly known in the constrained optimization literature.
  arXiv  Detail & Related papers  (2020-05-21T14:39:14Z)
• Text-based Question Answering from Information Retrieval and Deep Neural Network Perspectives: A Survey [0.0]
  Text-based Question Answering (QA) is a challenging task which aims at finding short concrete answers for users' questions. Deep learning approaches, which are the main focus of this paper, provide a powerful technique to learn multiple layers of representations and interaction between questions and texts.
  arXiv  Detail & Related papers  (2020-02-16T16:24:39Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.