Please use this identifier to cite or link to this item: https://hdl.handle.net/10356/89882
Full metadata record
DC FieldValueLanguage
dc.contributor.authorWei, Zhepeien
dc.contributor.authorWang, Dien
dc.contributor.authorZhang, Mingen
dc.contributor.authorTan, Ah-Hweeen
dc.contributor.authorMiao, Chunyanen
dc.contributor.authorZhou, Youen
dc.date.accessioned2019-07-17T01:33:46Zen
dc.date.accessioned2019-12-06T17:35:45Z-
dc.date.available2019-07-17T01:33:46Zen
dc.date.available2019-12-06T17:35:45Z-
dc.date.copyright2018-07-01en
dc.date.issued2018en
dc.identifier.citationWei, Z., Wang, D., Zhang, M., Tan, A.-H., Miao, C., & Zhou, Y. (2018). Autonomous agents in snake game via deep reinforcement learning. 2018 IEEE International Conference on Agents (ICA). doi:10.1109/AGENTS.2018.8460004en
dc.identifier.urihttps://hdl.handle.net/10356/89882-
dc.description.abstractSince DeepMind pioneered a deep reinforcement learning (DRL) model to play the Atari games, DRL has become a commonly adopted method to enable the agents to learn complex control policies in various video games. However, similar approaches may still need to be improved when applied to more challenging scenarios, where reward signals are sparse and delayed. In this paper, we develop a refined DRL model to enable our autonomous agent to play the classical Snake Game, whose constraint gets stricter as the game progresses. Specifically, we employ a convolutional neural network (CNN) trained with a variant of Q-learning. Moreover, we propose a carefully designed reward mechanism to properly train the network, adopt a training gap strategy to temporarily bypass training after the location of the target changes, and introduce a dual experience replay method to categorize different experiences for better training efficacy. The experimental results show that our agent outperforms the baseline model and surpasses human-level performance in terms of playing the Snake Game.en
dc.description.sponsorshipNRF (Natl Research Foundation, S’pore)en
dc.format.extent6 p.en
dc.language.isoenen
dc.rights© 2018 IEEE. Personal use of this material is permitted. Permission from IEEE must be obtained for all other uses, in any current or future media, including reprinting/republishing this material for advertising or promotional purposes, creating new collective works, for resale or redistribution to servers or lists, or reuse of any copyrighted component of this work in other works. The published version is available at: https://doi.org/10.1109/AGENTS.2018.8460004en
dc.subjectDeep Reinforcement Learningen
dc.subjectSnake Gameen
dc.subjectEngineering::Computer science and engineeringen
dc.titleAutonomous agents in snake game via deep reinforcement learningen
dc.typeConference Paperen
dc.contributor.schoolSchool of Computer Science and Engineeringen
dc.contributor.conference2018 IEEE International Conference on Agents (ICA)en
dc.identifier.doi10.1109/AGENTS.2018.8460004en
dc.description.versionAccepted versionen
dc.identifier.rims209586en
item.grantfulltextopen-
item.fulltextWith Fulltext-
Appears in Collections:SCSE Conference Papers
Files in This Item:
File Description SizeFormat 
ICA2018SnakeGame.pdf315.46 kBAdobe PDFThumbnail
View/Open

SCOPUSTM   
Citations 20

8
Updated on Jul 9, 2022

Page view(s)

329
Updated on Aug 18, 2022

Download(s) 5

478
Updated on Aug 18, 2022

Google ScholarTM

Check

Altmetric


Plumx

Items in DR-NTU are protected by copyright, with all rights reserved, unless otherwise indicated.