Matches in SemOpenAlex for { <https://semopenalex.org/work/W4316657872> ?p ?o ?g. }
Showing items 1 to 62 of
62
with 100 items per page.
- W4316657872 abstract "To perform well, Deep Reinforcement Learning (DRL) methods require significant memory resources and computational time. Also, sometimes these systems need additional environment information to achieve a good reward. However, it is more important for many applications and devices to reduce memory usage and computational times than to achieve the maximum reward. This paper presents a modified DRL method that performs reasonably well with compressed imagery data without requiring additional environment information and also uses less memory and time. We have designed a lightweight Convolutional Neural Network (CNN) with a variant of the Q-network that efficiently takes preprocessed image data as input and uses less memory. Furthermore, we use a simple reward mechanism and small experience replay memory so as to provide only the minimum necessary information. Our modified DRL method enables our autonomous agent to play Snake, a classical control game. The results show our model can achieve similar performance as other DRL methods." @default.
- W4316657872 created "2023-01-17" @default.
- W4316657872 creator A5001756756 @default.
- W4316657872 creator A5064624135 @default.
- W4316657872 date "2022-10-12" @default.
- W4316657872 modified "2023-09-27" @default.
- W4316657872 title "A Memory Efficient Deep Reinforcement Learning Approach For Snake Game Autonomous Agents" @default.
- W4316657872 cites W2114537044 @default.
- W4316657872 cites W2145339207 @default.
- W4316657872 cites W2593338657 @default.
- W4316657872 cites W2746553466 @default.
- W4316657872 cites W2787259794 @default.
- W4316657872 cites W2889665471 @default.
- W4316657872 cites W2904455790 @default.
- W4316657872 cites W32403112 @default.
- W4316657872 cites W4254755460 @default.
- W4316657872 cites W4362203700 @default.
- W4316657872 doi "https://doi.org/10.1109/aict55583.2022.10013603" @default.
- W4316657872 hasPublicationYear "2022" @default.
- W4316657872 type Work @default.
- W4316657872 citedByCount "0" @default.
- W4316657872 crossrefType "proceedings-article" @default.
- W4316657872 hasAuthorship W4316657872A5001756756 @default.
- W4316657872 hasAuthorship W4316657872A5064624135 @default.
- W4316657872 hasBestOaLocation W43166578722 @default.
- W4316657872 hasConcept C108583219 @default.
- W4316657872 hasConcept C111472728 @default.
- W4316657872 hasConcept C119857082 @default.
- W4316657872 hasConcept C138885662 @default.
- W4316657872 hasConcept C154945302 @default.
- W4316657872 hasConcept C2780586882 @default.
- W4316657872 hasConcept C41008148 @default.
- W4316657872 hasConcept C50644808 @default.
- W4316657872 hasConcept C81363708 @default.
- W4316657872 hasConcept C97541855 @default.
- W4316657872 hasConceptScore W4316657872C108583219 @default.
- W4316657872 hasConceptScore W4316657872C111472728 @default.
- W4316657872 hasConceptScore W4316657872C119857082 @default.
- W4316657872 hasConceptScore W4316657872C138885662 @default.
- W4316657872 hasConceptScore W4316657872C154945302 @default.
- W4316657872 hasConceptScore W4316657872C2780586882 @default.
- W4316657872 hasConceptScore W4316657872C41008148 @default.
- W4316657872 hasConceptScore W4316657872C50644808 @default.
- W4316657872 hasConceptScore W4316657872C81363708 @default.
- W4316657872 hasConceptScore W4316657872C97541855 @default.
- W4316657872 hasLocation W43166578721 @default.
- W4316657872 hasLocation W43166578722 @default.
- W4316657872 hasOpenAccess W4316657872 @default.
- W4316657872 hasPrimaryLocation W43166578721 @default.
- W4316657872 hasRelatedWork W2337926734 @default.
- W4316657872 hasRelatedWork W2731899572 @default.
- W4316657872 hasRelatedWork W3116150086 @default.
- W4316657872 hasRelatedWork W3133861977 @default.
- W4316657872 hasRelatedWork W4200173597 @default.
- W4316657872 hasRelatedWork W4311257506 @default.
- W4316657872 hasRelatedWork W4312417841 @default.
- W4316657872 hasRelatedWork W4320802194 @default.
- W4316657872 hasRelatedWork W4321369474 @default.
- W4316657872 hasRelatedWork W4366224123 @default.
- W4316657872 isParatext "false" @default.
- W4316657872 isRetracted "false" @default.
- W4316657872 workType "article" @default.