Attention-based Deep Reinforcement Learning for Multi-view Environments

被引:0
|
作者
Barati, Elaheh [1 ]
Chen, Xuewen [2 ]
Zhong, Zichun [1 ]
机构
[1] Wayne State Univ, Detroit, MI 48202 USA
[2] AIWAYS AUTO, Shanghai, Peoples R China
关键词
Reinforcement learning; Deep learning; Attention networks;
D O I
暂无
中图分类号
TP301 [理论、方法];
学科分类号
081202 ;
摘要
In reinforcement learning algorithms, it is a common practice to account for only a single view of the environment to make the desired decisions; however, utilizing multiple views of the environment can help to promote the learning of complicated policies. Since the views may frequently suffer from partial observability, their provided observation can have different levels of importance. In this paper, we present a novel attention-based deep reinforcement learning method in a multi-view environment in which each view can provide various representative information about the environment. Specifically, our method learns a policy to dynamically attend to views of the environment based on their importance in the decision-making process. We evaluate the performance of our method on TORCS racing car simulator and three other complex 3D environments with obstacles.
引用
收藏
页码:1805 / 1807
页数:3
相关论文
共 50 条
  • [41] Unbalanced Multi-view Deep Learning
    Xu, Cai
    Li, Zehui
    Guan, Ziyu
    Zhao, Wei
    Song, Xiangyu
    Wu, Yue
    Li, Jianxin
    PROCEEDINGS OF THE 31ST ACM INTERNATIONAL CONFERENCE ON MULTIMEDIA, MM 2023, 2023, : 3051 - 3059
  • [42] DRIBO: Robust Deep Reinforcement Learning via Multi-View Information Bottleneck
    Fan, Jiameng
    Li, Wenchao
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [43] Deep Multi-View Concept Learning
    Xu, Cai
    Guan, Ziyu
    Zhao, Wei
    Niu, Yunfei
    Wang, Quan
    Wang, Zhiheng
    PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 2898 - 2904
  • [44] Deep Multi-View Learning to Rank
    Cao, Guanqun
    Iosifidis, Alexandros
    Gabbouj, Moncef
    Raghavan, Vijay
    Gottumukkala, Raju
    IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING, 2021, 33 (04) : 1426 - 1438
  • [45] On Deep Multi-View Representation Learning
    Wang, Weiran
    Arora, Raman
    Livescu, Karen
    Bilmes, Jeff
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 37, 2015, 37 : 1083 - 1092
  • [46] Deep Partial Multi-View Learning
    Zhang, Changqing
    Cui, Yajie
    Han, Zongbo
    Zhou, Joey Tianyi
    Fu, Huazhu
    Hu, Qinghua
    IEEE TRANSACTIONS ON PATTERN ANALYSIS AND MACHINE INTELLIGENCE, 2022, 44 (05) : 2402 - 2415
  • [47] Deep Generative Multi-view Learning
    Karami, Mahdi
    MACHINE LEARNING AND KNOWLEDGE DISCOVERY IN DATABASES, ECML PKDD 2019, PT I, 2020, 1167 : 465 - 477
  • [48] AFSleepNet: Attention-Based Multi-View Feature Fusion Framework for Pediatric Sleep Staging
    Zhu, Yunfeng
    Wu, Yunxiao
    Wang, Zhiya
    Zhou, Ligang
    Chen, Chen
    Xu, Zhifei
    Chen, Wei
    IEEE Transactions on Neural Systems and Rehabilitation Engineering, 2024, 32 : 4022 - 4032
  • [49] Multi-view informed attention-based model for Irony and Satire detection in Spanish variants
    Ortega-Bueno, Reynier
    Rosso, Paolo
    Medina Pagola, Jose E.
    KNOWLEDGE-BASED SYSTEMS, 2022, 235
  • [50] Initial Task Allocation for Multi-Human Multi-Robot Teams with Attention-based Deep Reinforcement Learning
    Wang, Ruiqi
    Zhao, Dezhong
    Min, Byung-Cheol
    2023 IEEE/RSJ INTERNATIONAL CONFERENCE ON INTELLIGENT ROBOTS AND SYSTEMS (IROS), 2023, : 7915 - 7922