With the breakthrough of AlphaGo,deep reinforcement learning has become a recognized technique for solving sequential decision-making problems.Despite its reputation,data inefficiency caused by its trial and error lea...With the breakthrough of AlphaGo,deep reinforcement learning has become a recognized technique for solving sequential decision-making problems.Despite its reputation,data inefficiency caused by its trial and error learning mechanism makes deep reinforcement learning difficult to apply in a wide range of areas.Many methods have been developed for sample efficient deep reinforcement learning,such as environment modelling,experience transfer,and distributed modifications,among which distributed deep reinforcement learning has shown its potential in various applications,such as human-computer gaming and intelligent transportation.In this paper,we conclude the state of this exciting field,by comparing the classical distributed deep reinforcement learning methods and studying important components to achieve efficient distributed learning,covering single player single agent distributed deep reinforcement learning to the most complex multiple players multiple agents distributed deep reinforcement learning.Furthermore,we review recently released toolboxes that help to realize distributed deep reinforcement learning without many modifications of their non-distributed versions.By analysing their strengths and weaknesses,a multi-player multi-agent distributed deep reinforcement learning toolbox is developed and released,which is further validated on Wargame,a complex environment,showing the usability of the proposed toolbox for multiple players and multiple agents distributed deep reinforcement learning under complex games.Finally,we try to point out challenges and future trends,hoping that this brief review can provide a guide or a spark for researchers who are interested in distributed deep reinforcement learning.展开更多
Background:his paper presents a case study on 100Credit,an Internet credit service provider in China.100Credit began as an IT company specializing in e-commerce recommendation before getting into the credit rating bus...Background:his paper presents a case study on 100Credit,an Internet credit service provider in China.100Credit began as an IT company specializing in e-commerce recommendation before getting into the credit rating business.The company makes use of Big Data on multiple aspects of individuals’online activities to infer their potential credit risk.Methods:Based on 100Credit’s business practices,this paper summarizes four aspects related to the value of Big Data in Internet credit services.Results:1)value from large data volume that provides access to more borrowers;2)value from prediction correctness in reducing lenders’operational cost;3)value from the variety of services catering to different needs of lenders;and 4)value from information protection to sustain credit service businesses.Conclusion:The paper also discusses the opportunities and challenges of Big Databased credit risk analysis,which needs to be improved in future research and practice.展开更多
基金supported by Open Fund/Postdoctoral Fund of the Laboratory of Cognition and Decision Intelligence for Complex Systems,Institute of Automation,Chinese Academy of Sciences,China(No.CASIA-KFKTXDA27040809).
文摘With the breakthrough of AlphaGo,deep reinforcement learning has become a recognized technique for solving sequential decision-making problems.Despite its reputation,data inefficiency caused by its trial and error learning mechanism makes deep reinforcement learning difficult to apply in a wide range of areas.Many methods have been developed for sample efficient deep reinforcement learning,such as environment modelling,experience transfer,and distributed modifications,among which distributed deep reinforcement learning has shown its potential in various applications,such as human-computer gaming and intelligent transportation.In this paper,we conclude the state of this exciting field,by comparing the classical distributed deep reinforcement learning methods and studying important components to achieve efficient distributed learning,covering single player single agent distributed deep reinforcement learning to the most complex multiple players multiple agents distributed deep reinforcement learning.Furthermore,we review recently released toolboxes that help to realize distributed deep reinforcement learning without many modifications of their non-distributed versions.By analysing their strengths and weaknesses,a multi-player multi-agent distributed deep reinforcement learning toolbox is developed and released,which is further validated on Wargame,a complex environment,showing the usability of the proposed toolbox for multiple players and multiple agents distributed deep reinforcement learning under complex games.Finally,we try to point out challenges and future trends,hoping that this brief review can provide a guide or a spark for researchers who are interested in distributed deep reinforcement learning.
文摘Background:his paper presents a case study on 100Credit,an Internet credit service provider in China.100Credit began as an IT company specializing in e-commerce recommendation before getting into the credit rating business.The company makes use of Big Data on multiple aspects of individuals’online activities to infer their potential credit risk.Methods:Based on 100Credit’s business practices,this paper summarizes four aspects related to the value of Big Data in Internet credit services.Results:1)value from large data volume that provides access to more borrowers;2)value from prediction correctness in reducing lenders’operational cost;3)value from the variety of services catering to different needs of lenders;and 4)value from information protection to sustain credit service businesses.Conclusion:The paper also discusses the opportunities and challenges of Big Databased credit risk analysis,which needs to be improved in future research and practice.
