scholarly journals Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

2020 ◽  
Author(s):  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Yaser Faghan ◽  
Puhong Duan ◽  
Sina Faizollahzadeh Ardabili ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Dynamic Systems ◽  
State Of The Art ◽  
Economic Data ◽  
Economic Problems ◽  
Wide Range ◽  
Survey Results ◽  
Risk Parameters ◽  
Accuracy Performance ◽  
Insight Into

The popularity of deep reinforcement learning (DRL) methods in economics have been exponentially increased. DRL, through a wide range of capabilities from reinforcement learning (RL) to deep learning (DL), offers vast opportunities for handling sophisticated economics dynamic systems. DRL is characterized by scalability with the potential to be applied to high-dimensional problems in conjunction with noisy and nonlinear patterns of economic data. In this paper, we initially consider a brief review of DL, RL, and deep RL methods in diverse applications in economics, providing an in-depth insight into state of the art. Furthermore, the architecture of DRL applied to economic applications is investigated in order to highlight the complexity, robustness, accuracy, performance, computational tasks, risk constraints, and profitability. The survey results indicate that DRL can provide better performance and higher efficiency as compared to the traditional algorithms while facing real economic problems at the presence of risk parameters and the ever-increasing uncertainties.

scholarly journals Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

2020 ◽  
Author(s):  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Yaser Faghan ◽  
Puhong Duan ◽  
Sina Faizollahzadeh Ardabili ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Dynamic Systems ◽  
State Of The Art ◽  
Economic Data ◽  
Economic Problems ◽  
Wide Range ◽  
Survey Results ◽  
Risk Parameters ◽  
Accuracy Performance ◽  
Insight Into

The popularity of deep reinforcement learning (DRL) methods in economics have been exponentially increased. DRL, through a wide range of capabilities from reinforcement learning (RL) to deep learning (DL), offers vast opportunities for handling sophisticated economics dynamic systems. DRL is characterized by scalability with the potential to be applied to high-dimensional problems in conjunction with noisy and nonlinear patterns of economic data. In this paper, we initially consider a brief review of DL, RL, and deep RL methods in diverse applications in economics, providing an in-depth insight into state of the art. Furthermore, the architecture of DRL applied to economic applications is investigated in order to highlight the complexity, robustness, accuracy, performance, computational tasks, risk constraints, and profitability. The survey results indicate that DRL can provide better performance and higher efficiency as compared to the traditional algorithms while facing real economic problems at the presence of risk parameters and the ever-increasing uncertainties.

scholarly journals Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

2020 ◽  
Author(s):  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Yaser Faghan ◽  
Puhong Duan ◽  
Sina Faizollahzadeh Ardabili ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Dynamic Systems ◽  
State Of The Art ◽  
Economic Data ◽  
Economic Problems ◽  
Wide Range ◽  
Survey Results ◽  
Risk Parameters ◽  
Accuracy Performance ◽  
Insight Into

The popularity of deep reinforcement learning (DRL) methods in economics have been exponentially increased. DRL, through a wide range of capabilities from reinforcement learning (RL) to deep learning (DL), offers vast opportunities for handling sophisticated economics dynamic systems. DRL is characterized by scalability with the potential to be applied to high-dimensional problems in conjunction with noisy and nonlinear patterns of economic data. In this paper, we initially consider a brief review of DL, RL, and deep RL methods in diverse applications in economics, providing an in-depth insight into state of the art. Furthermore, the architecture of DRL applied to economic applications is investigated in order to highlight the complexity, robustness, accuracy, performance, computational tasks, risk constraints, and profitability. The survey results indicate that DRL can provide better performance and higher efficiency as compared to the traditional algorithms while facing real economic problems at the presence of risk parameters and the ever-increasing uncertainties.

scholarly journals Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

2020 ◽  
Author(s):  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Yaser Faghan ◽  
Puhong Duan ◽  
Sina Faizollahzadeh Ardabili ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Dynamic Systems ◽  
State Of The Art ◽  
Economic Data ◽  
Economic Problems ◽  
Wide Range ◽  
Survey Results ◽  
Risk Parameters ◽  
Accuracy Performance ◽  
Insight Into

The popularity of deep reinforcement learning (DRL) methods in economics have been exponentially increased. DRL, through a wide range of capabilities from reinforcement learning (RL) to deep learning (DL), offers vast opportunities for handling sophisticated economics dynamic systems. DRL is characterized by scalability with the potential to be applied to high-dimensional problems in conjunction with noisy and nonlinear patterns of economic data. In this paper, we initially consider a brief review of DL, RL, and deep RL methods in diverse applications in economics, providing an in-depth insight into state of the art. Furthermore, the architecture of DRL applied to economic applications is investigated in order to highlight the complexity, robustness, accuracy, performance, computational tasks, risk constraints, and profitability. The survey results indicate that DRL can provide better performance and higher efficiency as compared to the traditional algorithms while facing real economic problems at the presence of risk parameters and the ever-increasing uncertainties.

scholarly journals Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

2020 ◽  
Author(s):  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Yaser Faghan ◽  
Puhong Duan ◽  
Sina Faizollahzadeh Ardabili ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
Dynamic Systems ◽  
State Of The Art ◽  
Economic Data ◽  
Economic Problems ◽  
Wide Range ◽  
Survey Results ◽  
Risk Parameters ◽  
Accuracy Performance ◽  
Insight Into

The popularity of deep reinforcement learning (DRL) methods in economics have been exponentially increased. DRL, through a wide range of capabilities from reinforcement learning (RL) to deep learning (DL), offers vast opportunities for handling sophisticated economics dynamic systems. DRL is characterized by scalability with the potential to be applied to high-dimensional problems in conjunction with noisy and nonlinear patterns of economic data. In this paper, we initially consider a brief review of DL, RL, and deep RL methods in diverse applications in economics, providing an in-depth insight into state of the art. Furthermore, the architecture of DRL applied to economic applications is investigated in order to highlight the complexity, robustness, accuracy, performance, computational tasks, risk constraints, and profitability. The survey results indicate that DRL can provide better performance and higher efficiency as compared to the traditional algorithms while facing real economic problems at the presence of risk parameters and the ever-increasing uncertainties.

scholarly journals Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

Mathematics ◽  
2020 ◽  
Vol 8 (10) ◽  
pp. 1640 ◽  
Author(s):  
Amirhosein Mosavi ◽  
Yaser Faghan ◽  
Pedram Ghamisi ◽  
Puhong Duan ◽  
Sina Faizollahzadeh Ardabili ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
High Dimensional ◽  
Economic Data ◽  
Economic Problems ◽  
Wide Range ◽  
Survey Results ◽  
Risk Parameters ◽  
Accuracy Performance ◽  
Insight Into

The popularity of deep reinforcement learning (DRL) applications in economics has increased exponentially. DRL, through a wide range of capabilities from reinforcement learning (RL) to deep learning (DL), offers vast opportunities for handling sophisticated dynamic economics systems. DRL is characterized by scalability with the potential to be applied to high-dimensional problems in conjunction with noisy and nonlinear patterns of economic data. In this paper, we initially consider a brief review of DL, RL, and deep RL methods in diverse applications in economics, providing an in-depth insight into the state-of-the-art. Furthermore, the architecture of DRL applied to economic applications is investigated in order to highlight the complexity, robustness, accuracy, performance, computational tasks, risk constraints, and profitability. The survey results indicate that DRL can provide better performance and higher efficiency as compared to the traditional algorithms while facing real economic problems in the presence of risk parameters and the ever-increasing uncertainties.

scholarly journals Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

2020 ◽  
Author(s):  
Amir Mosavi ◽  
Yaser Faghan ◽  
Pedram Ghamisi ◽  
Puhong Duan ◽  
Sina Faizollahzadeh Ardabili ◽  
...  
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
High Dimensional ◽  
Economic Data ◽  
Economic Problems ◽  
Wide Range ◽  
Survey Results ◽  
Risk Parameters ◽  
Accuracy Performance ◽  
Insight Into

The popularity of deep reinforcement learning (DRL) applications in economics has increased exponentially. DRL, through a wide range of capabilities from reinforcement learning (RL) to deep learning (DL), offers vast opportunities for handling sophisticated dynamic economics systems. DRL is characterized by scalability with the potential to be applied to high-dimensional problems in conjunction with noisy and nonlinear patterns of economic data. In this paper, we initially consider a brief review of DL, RL, and deep RL methods in diverse applications in economics, providing an in-depth insight into the state-of-the-art. Furthermore, the architecture of DRL applied to economic applications is investigated in order to highlight the complexity, robustness, accuracy, performance, computational tasks, risk constraints, and profitability. The survey results indicate that DRL can provide better performance and higher efficiency as compared to the traditional algorithms while facing real economic problems in the presence of risk parameters and the ever-increasing uncertainties.

scholarly journals Comprehensive Review of Deep Reinforcement Learning Methods and Applications in Economics

2020 ◽  
Author(s):  
Amir Mosavi ◽  
Pedram Ghamisi ◽  
Yaser Faghan ◽  
Puhong Duan ◽  
Shahab Shamshirband
Keyword(s):  
Reinforcement Learning ◽  
State Of The Art ◽  
Economic Data ◽  
Economic Problems ◽  
Business Environments ◽  
Wide Range ◽  
Survey Results ◽  
Risk Parameters ◽  
Accuracy Performance ◽  
Insight Into

The popularity of deep reinforcement learning (DRL) methods in economics have been exponentially increased. DRL through a wide range of capabilities from reinforcement learning (RL) and deep learning (DL) for handling sophisticated dynamic business environments offers vast opportunities. DRL is characterized by scalability with the potential to be applied to high-dimensional problems in conjunction with noisy and nonlinear patterns of economic data. In this work, we first consider a brief review of DL, RL, and deep RL methods in diverse applications in economics providing an in-depth insight into the state of the art. Furthermore, the architecture of DRL applied to economic applications is investigated in order to highlight the complexity, robustness, accuracy, performance, computational tasks, risk constraints, and profitability. The survey results indicate that DRL can provide better performance and higher accuracy as compared to the traditional algorithms while facing real economic problems at the presence of risk parameters and the ever-increasing uncertainties.

JAZZ MELODY GENERATION USING RECURRENT NETWORKS AND REINFORCEMENT LEARNING

2006 ◽  
Vol 15 (04) ◽  
pp. 623-650
Author(s):  
JUDY A. FRANKLIN
Keyword(s):  
Reinforcement Learning ◽  
Dynamic Systems ◽  
Recurrent Neural Networks ◽  
Short Term Memory ◽  
State Of The Art ◽  
Recurrent Network ◽  
Recurrent Networks ◽  
Short Term ◽  
Long Short Term Memory ◽  
Lstm Network

Recurrent (neural) networks have been deployed as models for learning musical processes, by computational scientists who study processes such as dynamic systems. Over time, more intricate music has been learned as the state of the art in recurrent networks improves. One particular recurrent network, the Long Short-Term Memory (LSTM) network shows promise for learning long songs, and generating new songs. We are experimenting with a module containing two inter-recurrent LSTM networks to cooperatively learn several human melodies, based on the songs' harmonic structures, and on the feedback inherent in the network. We show that these networks can learn to reproduce four human melodies. We then present as input new harmonizations, so as to generate new songs. We describe the reharmonizations, and show the new melodies that result. We also present a hierarchical structure for using reinforcement learning to choose LSTM modules during the course of melody generation.

scholarly journals Determining female consumer’s insight into products and shopping

2017 ◽  
Vol 10 (1) ◽  
pp. 14-23
Keyword(s):  
Product Development ◽  
Clothing Industry ◽  
South East Asia ◽  
Qualitative And Quantitative ◽  
Shopping Behaviour ◽  
Wide Range ◽  
Survey Results ◽  
The Right ◽  
Depth Interviews ◽  
Insight Into

This research explores consumer’s insight into the female sportswear segment for the purpose of improving product development in the clothing industry in South-East Asia, a consumer base consisting of 500 million people. The research aims to clarify the important parameters on which buying decisions are made. The parameters are based on price, function, fit, brand, and design. The methodology used in this research is qualitative and quantitative consisting of participative observations, in-depth interviews, and survey. Results shows a wide range of shopping approaches utilized by consumers. Shopping behaviour can be seen depending on products and location. Essential parameters for an exercising garment are fit and design. abundance of available options in the market can cause confusion amongst consumers. The over-availability of products contributed to the creation of such confusion or even fussiness amongst consumers. This is to suggest that the more alternatives available to consumers, the more difficult it will be to find “the right” product. Findings also suggests that consumer’s input and opinion is vital to product development and significantly contributes to product design and enhancement.

scholarly journals Glycosynthesis in a waterworld: new insight into the molecular basis of transglycosylation in retaining glycoside hydrolases

2015 ◽  
Vol 467 (1) ◽  
pp. 17-35 ◽  
Author(s):  
Bastien Bissaro ◽  
Pierre Monsan ◽  
Régis Fauré ◽  
Michael J. O’Donohue
Keyword(s):  
Molecular Basis ◽  
State Of The Art ◽  
Careful Analysis ◽  
Glycoside Hydrolases ◽  
Rational Basis ◽  
Substrate Specificities ◽  
Glycosidic Bonds ◽  
Hydrolytic Reaction ◽  
Wide Range ◽  
Insight Into

Carbohydrates are ubiquitous in Nature and play vital roles in many biological systems. Therefore the synthesis of carbohydrate-based compounds is of considerable interest for both research and commercial purposes. However, carbohydrates are challenging, due to the large number of sugar subunits and the multiple ways in which these can be linked together. Therefore, to tackle the challenge of glycosynthesis, chemists are increasingly turning their attention towards enzymes, which are exquisitely adapted to the intricacy of these biomolecules. In Nature, glycosidic linkages are mainly synthesized by Leloir glycosyltransferases, but can result from the action of non-Leloir transglycosylases or phosphorylases. Advantageously for chemists, non-Leloir transglycosylases are glycoside hydrolases, enzymes that are readily available and exhibit a wide range of substrate specificities. Nevertheless, non-Leloir transglycosylases are unusual glycoside hydrolases in as much that they efficiently catalyse the formation of glycosidic bonds, whereas most glycoside hydrolases favour the mechanistically related hydrolysis reaction. Unfortunately, because non-Leloir transglycosylases are almost indistinguishable from their hydrolytic counterparts, it is unclear how these enzymes overcome the ubiquity of water, thus avoiding the hydrolytic reaction. Without this knowledge, it is impossible to rationally design non-Leloir transglycosylases using the vast diversity of glycoside hydrolases as protein templates. In this critical review, a careful analysis of literature data describing non-Leloir transglycosylases and their relationship to glycoside hydrolase counterparts is used to clarify the state of the art knowledge and to establish a new rational basis for the engineering of glycoside hydrolases.

Sign in / Sign up

Export Citation Format

Share Document