Deep Reinforcement Learning: A Brief Survey

Arulkumaran, Kai; Deisenroth, Marc Peter; Brundage, Miles; Bharath, Anil A.

doi:10.1109/msp.2017.2743240

Cited by 2,821 publications

(1,283 citation statements)

References 34 publications

Supporting

Mentioning

1,081

Contrasting

Unclassified

Order By: Relevance

“…On the other hand, UCB encourages exploration in states with high uncertainty, whilst exploitation is encouraged in regions with high confidence. Therefore, intrinsic motivation is implemented in the system, encouraging the agent to learn about its environment, whilst exploitation can be taken advantage of in states which have already been explored adequately [51], [117]- [119]. Other approaches have sought to use supervised learning as a pre-training step to get the advantages of both reinforcement and supervised learning.…”

Section: B Longitudinal Control Systemsmentioning

confidence: 99%

A Survey of Deep Learning Applications to Autonomous Vehicle Control

Kuutti

Bowden

Jin

et al. 2021

IEEE Trans. Intell. Transport. Syst.

457

182

View full text Add to dashboard Cite

Designing a controller for autonomous vehicles capable of providing adequate performance in all driving scenarios is challenging due to the highly complex environment and inability to test the system in the wide variety of scenarios which it may encounter after deployment. However, deep learning methods have shown great promise in not only providing excellent performance for complex and non-linear control problems, but also in generalising previously learned rules to new scenarios. For these reasons, the use of deep learning for vehicle control is becoming increasingly popular. Although important advancements have been achieved in this field, these works have not been fully summarised. This paper surveys a wide range of research works reported in the literature which aim to control a vehicle through deep learning methods. Although there exists overlap between control and perception, the focus of this paper is on vehicle control, rather than the wider perception problem which includes tasks such as semantic segmentation and object detection. The paper identifies the strengths and limitations of available deep learning methods through comparative analysis and discusses the research challenges in terms of computation, architecture selection, goal specification, generalisation, verification and validation, as well as safety. Overall, this survey brings timely and topical information to a rapidly evolving field relevant to intelligent transportation systems.

show abstract

Section: B Longitudinal Control Systemsmentioning

confidence: 99%

A Survey of Deep Learning Applications to Autonomous Vehicle Control

Kuutti

Bowden

Jin

et al. 2021

IEEE Trans. Intell. Transport. Syst.

457

182

View full text Add to dashboard Cite

show abstract

“…Such an HL system is represented by DRL, which integrates RL and DL. The basic principle of DRL is presented in Figure . DRL has strong hybrid intelligence and will be one of the important future development directions of AI.…”

Section: Hybrid Learningmentioning

confidence: 99%

“…DRL has strong hybrid intelligence and will be one of the important future development directions of AI. Currently, DRL is poised to revolutionize the field of AI, and it represents a step toward building autonomous systems that possess a higher‐level understanding of the visual world . For example, DRL algorithms are being applied to robotics, which allows control policies for robots to be learned directly from real‐world camera input.…”

Section: Hybrid Learningmentioning

confidence: 99%

A new generation of AI: A review and perspective on machine learning technologies applied to smart energy and electric power systems

Cheng

2019

Int J Energy Res

216

View full text Add to dashboard Cite

Summary The new generation of artificial intelligence (AI), called AI 2.0, has recently become a research focus. Data‐driven AI 2.0 will accelerate the development of smart energy and electric power system (Smart EEPS). In AI 2.0, machine learning (ML) forms a typical representative algorithm category used to achieve predictions and judgments by analyzing and learning from massive amounts of historical and synthetic data to help people make optimal decisions. ML has preliminarily been applied to the Smart Grid (SG) and Energy Internet (EI) fields, which are important Smart EEPS representatives. AI 2.0, especially ML, is undergoing a critical period of rapid development worldwide and will play an essential role in Smart EEPS. In this context, this study, combined with the emerging SG and EI technologies, takes the typical representative of AI 2.0—ML—as the research objective and reviews its research status in the operation, optimization, control, dispatching, and management of SG and EI. The paper focuses on introducing and summarizing the mainstream uses of seven representative ML methods, including reinforcement learning, deep learning, transfer learning, parallel learning, hybrid learning, adversarial learning, and ensemble learning, in the SG and EI fields. In this survey, we begin with an introduction to these seven types of ML methods and then systematically review their applications in Smart EEPS. Finally, we discuss ML development under the big data thinking and offer a prospect for the future development of AI 2.0 and ML in Smart EEPS. We conduct this survey intended to arouse the interest and excitement of experts and scholars in the EEPS industry and to look ahead to efforts that jointly promote the rapid development of AI 2.0 in the Smart EEPS field.

show abstract

“…Deep learning is a method based on characterizing and learning data. Its feature learning and efficient algorithm for hierarchical feature extraction can overcome the problem of artificially acquiring features [14,15].…”

Section: Introductionmentioning

confidence: 99%

Recognition method of voltage sag causes based on Bi‐LSTM

Zheng

Wang

et al. 2019

IEEJ Transactions Elec Engng

View full text Add to dashboard Cite

In recent years, the power quality problem has become more complicated in power grids because of the extensive usage of power electronics and multisource multitransformation features. The method, based on physical characteristics such as time domain, frequency domain and transform domain, is facing challenges in terms of adaptability, algorithm efficiency and accuracy for the recognition of complex disturbance recognition. The bidirectional long short-term memory network is an algorithm in deep learning. It is based on data for characterization learning, which can effectively overcome the problem of information loss and generalization ability of physical methods. Moreover, it has the characteristics of memory, which can simultaneously consider historical information and future information and can better learn data features with time series characteristics. Aiming at the transient voltage sag time series data, this paper proposes a recognition method of the voltage sag causes based on the bidirectional long short-term memory network's extraction eigenvalue, the full-connection layer's high-dimensional feature extraction and the Softmax network layer's classification. The experiment uses simulation data and measured data to prove that the model has good recognition ability and good antinoise performance in the recognition of voltage sag causes and can be reliably applied in practical engineering.

show abstract

Deep Reinforcement Learning: A Brief Survey

Cited by 2,821 publications

References 34 publications

A Survey of Deep Learning Applications to Autonomous Vehicle Control

A Survey of Deep Learning Applications to Autonomous Vehicle Control

A new generation of AI: A review and perspective on machine learning technologies applied to smart energy and electric power systems

Recognition method of voltage sag causes based on Bi‐LSTM

Contact Info

Product

Resources

About