Please use this identifier to cite or link to this item:
https://www.um.edu.mt/library/oar/handle/123456789/82003
Full metadata record
DC Field | Value | Language |
---|---|---|
dc.contributor.author | Ye, Chang | - |
dc.contributor.author | Khalifa, Ahmed | - |
dc.contributor.author | Bontrager, Philip | - |
dc.contributor.author | Togelius, Julian | - |
dc.date.accessioned | 2021-10-12T07:28:41Z | - |
dc.date.available | 2021-10-12T07:28:41Z | - |
dc.date.issued | 2020 | - |
dc.identifier.citation | Ye, C., Khalifa, A., Bontrager, P., & Togelius, J. (2020). Rotation, translation, and cropping for zero-shot generalization. 2020 IEEE Conference on Games (CoG), Osaka. 57-64. | en_GB |
dc.identifier.uri | https://www.um.edu.mt/library/oar/handle/123456789/82003 | - |
dc.description.abstract | Deep Reinforcement Learning (DRL) has shown impressive performance on domains with visual inputs, in particular various games. However, the agent is usually trained on a fixed environment, e.g. a fixed number of levels. A growing mass of evidence suggests that these trained models fail to generalize to even slight variations of the environments they were trained on. This paper advances the hypothesis that the lack of generalization is partly due to the input representation, and explores how rotation, cropping and translation could increase generality. We show that a cropped, translated and rotated observation can get better generalization on unseen levels of two-dimensional arcade games from the GVGAI framework. The generality of the agents is evaluated on both human-designed and procedurally generated levels. | en_GB |
dc.language.iso | en | en_GB |
dc.publisher | Institute of Electrical and Electronics Engineers | en_GB |
dc.rights | info:eu-repo/semantics/restrictedAccess | en_GB |
dc.subject | Computer games -- Design | en_GB |
dc.subject | Image processing | en_GB |
dc.subject | Artificial intelligence | en_GB |
dc.subject | Machine learning | en_GB |
dc.title | Rotation, translation, and cropping for zero-shot generalization | en_GB |
dc.type | conferenceObject | en_GB |
dc.rights.holder | The copyright of this work belongs to the author(s)/publisher. The rights of this work are as defined by the appropriate Copyright Legislation or as modified by any successive legislation. Users may access this work and can make use of the information contained in accordance with the Copyright Legislation provided that the author must be properly acknowledged. Further distribution or reproduction in any format is prohibited without the prior permission of the copyright holder. | en_GB |
dc.bibliographicCitation.conferencename | 2020 IEEE Conference on Games (CoG) | en_GB |
dc.bibliographicCitation.conferenceplace | Osaka, Japan, 24-27/08/2020 | en_GB |
dc.description.reviewed | peer-reviewed | en_GB |
dc.identifier.doi | 10.1109/CoG47356.2020.9231907 | - |
Appears in Collections: | Scholarly Works - InsDG |
Files in This Item:
File | Description | Size | Format | |
---|---|---|---|---|
Rotation_Translation_and_Cropping_for_Zero-Shot_Generalization_2020.pdf Restricted Access | 2.66 MB | Adobe PDF | View/Open Request a copy |
Items in OAR@UM are protected by copyright, with all rights reserved, unless otherwise indicated.