Deep Active Learning for Autonomous Navigation

Hussein, Ahmed; Gaber, Mohamed Medhat; Elyan, Eyad

doi:10.1007/978-3-319-44188-7_1

Cited by 9 publications

(7 citation statements)

References 24 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To overcome this limitation, recent developments combine RL techniques with the significant feature extraction and processing capabilities of deep learning models in a framework known as Deep Q-Network (DQN) [6]. This approach exploits deep neural networks for both feature selection and Q-function approximation, hence enabling unprecedented performance in complex settings such as learning efficient playing strategies from unlabeled video frames of Atari games [7], robotic manipulation [8], and autonomous navigation of aerial [9] and ground vehicles [10].…”

Section: Introductionmentioning

confidence: 99%

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

Behzadan

Munir

2017

Lecture Notes in Computer Science

188

158

View full text Add to dashboard Cite

Abstract. Deep learning classifiers are known to be inherently vulnerable to manipulation by intentionally perturbed inputs, named adversarial examples. In this work, we establish that reinforcement learning techniques based on Deep Q-Networks (DQNs) are also vulnerable to adversarial input perturbations, and verify the transferability of adversarial examples across different DQN models. Furthermore, we present a novel class of attacks based on this vulnerability that enable policy manipulation and induction in the learning process of DQNs. We propose an attack mechanism that exploits the transferability of adversarial examples to implement policy induction attacks on DQNs, and demonstrate its efficacy and impact through experimental study of a game-learning scenario.

show abstract

Section: Introductionmentioning

confidence: 99%

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

Behzadan

Munir

2017

Lecture Notes in Computer Science

188

158

View full text Add to dashboard Cite

show abstract

“…The results are conducted on a 2D navigation task and show that the proposed reward shaping approach speeds up and improves deep reinforcement learning and provides increased stability against exploration policies. Our next step is to test the proposed approach on learning various navigation tasks in a more realistic simulator [38]. We also aim to incorporate reward shaping from demonstration with A3C [6] which is considered the current state of the art in deep reinforcement learning.…”

Section: Discussionmentioning

confidence: 99%

Deep reward shaping from demonstrations

Hussein

Elyan

Gaber

et al. 2017

2017 International Joint Conference on Neural Networks (IJCNN)

Self Cite

View full text Add to dashboard Cite

“…For example, [70] proposes to use imitation learning to perform navigation tasks. The visual environment and actions taken by the teacher viewed from a first-person perspective are used as the training set.…”

Section: Video Processingmentioning

confidence: 99%

“…When performing tasks, students use deep convolutional neural networks for feature extraction, learn imitation strategies, and further use the AL method to select samples with insufficient confidence, which are added to the training set to update the action strategy. [70] significantly improves the initial strategy using fewer samples. DeActive [66] proposed a DAL activity recognition model.…”

Section: Video Processingmentioning

confidence: 99%

A Survey of Deep Active Learning

Ren¹,

Xiao²,

Chang³

et al. 2020

Preprint

View full text Add to dashboard Cite

Active learning (AL) attempts to maximize a model's performance gain while annotating the fewest samples possible. Deep learning (DL) is greedy for data and requires a large amount of data supply to optimize a massive number of parameters if the model is to learn how to extract high-quality features. In recent years, due to the rapid development of internet technology, we have entered an era of information abundance characterized by massive amounts of available data. As a result, DL has attracted significant attention from researchers and has been rapidly developed. Compared with DL, however, researchers have relatively low interest in AL. This is mainly because before the rise of DL, traditional machine learning requires relatively few labeled samples, meaning that early AL is rarely accorded the value it deserves. Although DL has made breakthroughs in various fields, most of this success is due to the large number of publicly available annotated datasets. However, the acquisition of a large number of high-quality annotated datasets consumes a lot of manpower, making it unfeasible in fields that require high levels of expertise (such as speech recognition, information extraction, medical images, etc.) Therefore, AL is gradually coming to receive the attention it is due.It is therefore natural to investigate whether AL can be used to reduce the cost of sample annotations, while retaining the powerful learning capabilities of DL. As a result of such investigations, deep active learning (DAL) has emerged. Although research on this topic is quite abundant, there has not yet been a comprehensive survey of DAL-related works; accordingly, this article aims to fill this gap. We provide a formal classification method for the existing work, along with a comprehensive and systematic overview. In addition, we also analyze and summarize the development of DAL from an application perspective. Finally, we discuss the confusion and problems associated with DAL and provide some possible development directions.CCS Concepts: • Computing methodologies → Machine learning algorithms.

show abstract

Deep Active Learning for Autonomous Navigation

Cited by 9 publications

References 24 publications

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

Vulnerability of Deep Reinforcement Learning to Policy Induction Attacks

Deep reward shaping from demonstrations

A Survey of Deep Active Learning

Contact Info

Product

Resources

About