DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ko, Wonschick | ko |
dc.contributor.author | Chang, Dong Eui | ko |
dc.date.accessioned | 2019-11-26T07:21:21Z | - |
dc.date.available | 2019-11-26T07:21:21Z | - |
dc.date.created | 2019-11-25 | - |
dc.date.created | 2019-11-25 | - |
dc.date.created | 2019-11-25 | - |
dc.date.created | 2019-11-25 | - |
dc.date.issued | 2019-10-17 | - |
dc.identifier.citation | 19th International Conference on Control, Automation and Systems (ICCAS), pp.1483 - 1486 | - |
dc.identifier.issn | 2093-7121 | - |
dc.identifier.uri | http://hdl.handle.net/10203/268600 | - |
dc.description.abstract | In this paper, we propose a dual memory structure for reinforcement learning algorithms with replay memory. The dual memory consists of a main memory that stores various data and a cache memory that manages the data and trains the reinforcement learning agent efficiently. Experimental results show that the dual memory structure achieves higher training and test scores than the conventional single memory structure in three selected environments of OpenAI Gym. This implies that the dual memory structure enables better and more efficient training than the single memory structure. | - |
dc.language | English | - |
dc.publisher | ICROS | - |
dc.title | A dual memory structure for efficient use of replay memory in deep reinforcement learning | - |
dc.type | Conference | - |
dc.identifier.wosid | 000555707100216 | - |
dc.identifier.scopusid | 2-s2.0-85079089938 | - |
dc.type.rims | CONF | - |
dc.citation.beginningpage | 1483 | - |
dc.citation.endingpage | 1486 | - |
dc.citation.publicationname | 19th International Conference on Control, Automation and Systems (ICCAS) | - |
dc.identifier.conferencecountry | KO | - |
dc.identifier.conferencelocation | ICC Jeju | - |
dc.identifier.doi | 10.23919/ICCAS47443.2019.8971629 | - |
dc.contributor.localauthor | Chang, Dong Eui | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.