Information, Computing and Intelligent systems最新文献

筛选

英文中文

USAK METHOD FOR THE REINFORCEMENT LEARNING Usak方法用于强化学习

Information, Computing and Intelligent systems Pub Date : 2020-10-01 DOI: 10.20535/2708-4930.1.2020.216042

M. Novotarskyi, V. Kuzmich

{"title":"USAK METHOD FOR THE REINFORCEMENT LEARNING","authors":"M. Novotarskyi, V. Kuzmich","doi":"10.20535/2708-4930.1.2020.216042","DOIUrl":"https://doi.org/10.20535/2708-4930.1.2020.216042","url":null,"abstract":"In the field of reinforcement learning, tabular methods have become widespread. There are many important scientific results, which significantly improve their performance in specific applications. However, the application of tabular methods is limited due to the large amount of resources required to store value functions in tabular form under high-dimensional state spaces. A natural solution to the memory problem is to use parameterized function approximations. However, conventional approaches to function approximations, in most cases, have ceased to give the desired result of memory reduction in solving realworld problems. This fact became the basis for the application of new approaches, one of which is the use of Sparse Distributed Memory (SDM) based on Kanerva coding. A further development of this direction was the method of Similarity-Aware Kanerva (SAK). In this paper, a modification of the SAK method is proposed, the Uniform Similarity-Aware Kanerva (USAK) method, which is based on the uniform distribution of prototypes in the state space. This approach has reduced the use of RAM required to store prototypes. In addition, reducing the receptive distance of each of the prototypes made it possible to increase the learning speed by reducing the number of calculations in the linear approximator.","PeriodicalId":411692,"journal":{"name":"Information, Computing and Intelligent systems","volume":"C-17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126760141","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 0

PETRI-OBJECT SIMULATION: TECHNIQUE AND SOFTWARE Petri-object仿真:技术与软件

Information, Computing and Intelligent systems Pub Date : 2020-10-01 DOI: 10.20535/2708-4930.1.2020.216057

I. V. Stetsenko, A. Dyfuchyn

{"title":"PETRI-OBJECT SIMULATION: TECHNIQUE AND SOFTWARE","authors":"I. V. Stetsenko, A. Dyfuchyn","doi":"10.20535/2708-4930.1.2020.216057","DOIUrl":"https://doi.org/10.20535/2708-4930.1.2020.216057","url":null,"abstract":"Nowadays information systems tend to be including components for transforming data into information applying modelling and simulation. Combined with real-time data, discrete event simulation could create powerful making decision and control systems. For these purposes, simulation software should be concentrated on creation the model as a code which can be easy integrated with other components of software. In this regard, Petri-object simulation technique, the main concept of which is to compose the code of model of complicated discrete event system in a fast and flexible way, simultaneously providing fast running the simulation, is requisite. The behaviour description of the model based on stochastic multichannel Petri net while the model composition is grounded on object-oriented technology. The Petri-object simulation software provides scalable simulation algorithm, graphical editor, correct transformation graphical images into model, correct simulation results. Graphical editor helps to cope with error-prone process of linking elements with each other. For better understanding the technique, the Petri-object model of web information system has been developed. Investigation of the response time has been conducted. The experiment has revealed system parameters impact on the value of response time. Thus, the model can be useful to avoid long-running request.","PeriodicalId":411692,"journal":{"name":"Information, Computing and Intelligent systems","volume":"183 3 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-10-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133348403","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 3

首页上一页