Attentive Relation Network for Object based Video Games

Hangyu Deng, Jia Luo, Jinglu Hu

研究成果: Conference contribution

抄録

Deep reinforcement learning algorithms have made great progress in video games. However, there are still some problems, such as sample inefficiency and poor generalization. In this paper, we highlight that these problems are partially caused by the inability of convolutional neural networks (CNNs) to reason with the underlying relations between the objects in the image observations. Based on this point, we try to alleviate these problems in a more efficient and explainable way, including learning the representations of objects and reasoning the relations between them with a relation network (RN). Each pixel in the feature maps is treated as an object and our model explicitly learns the relations between object pairs. The relations are summarized through an attention mechanism and then fed into the downstream fully-connected layers. In the experiments, our model is compared with baseline models in three typical object based Atari games. Under the same hyperparameter settings, our model still achieves better sample efficiency and generalization capability. Further studies throw light on the impact of hyperparameters and verify the interpretability of the model.

本文言語English
ホスト出版物のタイトルIJCNN 2021 - International Joint Conference on Neural Networks, Proceedings
出版社Institute of Electrical and Electronics Engineers Inc.
ISBN(電子版)9780738133669
DOI
出版ステータスPublished - 2021 7 18
イベント2021 International Joint Conference on Neural Networks, IJCNN 2021 - Virtual, Shenzhen, China
継続期間: 2021 7 182021 7 22

出版物シリーズ

名前Proceedings of the International Joint Conference on Neural Networks
2021-July

Conference

Conference2021 International Joint Conference on Neural Networks, IJCNN 2021
国/地域China
CityVirtual, Shenzhen
Period21/7/1821/7/22

ASJC Scopus subject areas

  • ソフトウェア
  • 人工知能

フィンガープリント

「Attentive Relation Network for Object based Video Games」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル