Generative Hybrid Representations for Activity Forecasting with No-Regret Learning

被引:48
|
作者
Guan, Jiaqi [1 ,2 ]
Yuan, Ye [1 ]
Kitani, Kris M. [1 ]
Rhinehart, Nicholas [1 ,3 ]
机构
[1] Carnegie Mellon Univ, Pittsburgh, PA 15213 USA
[2] Univ Illinois, Champaign, IL 61820 USA
[3] Univ Calif Berkeley, Berkeley, CA USA
关键词
D O I
10.1109/CVPR42600.2020.00025
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
Automatically reasoning about future human behaviors is a difficult problem but has significant practical applications to assistive systems. Part of this difficulty stems from learning systems' inability to represent all kinds of behaviors. Some behaviors, such as motion, are best described with continuous representations, whereas others, such as picking up a cup, are best described with discrete representations. Furthermore, human behavior is generally not fixed: people can change their habits and routines. This suggests these systems must be able to learn and adapt continuously. In this work, we develop an efficient deep generative model to jointly forecast a person's future discrete actions and continuous motions. On a large-scale egocentric dataset, EPIC-KITCHENS, we observe our method generates high-quality and diverse samples while exhibiting better generalization than related generative models. Finally, we propose a variant to continually learn our model from streaming data, observe its practical effectiveness, and theoretically justify its learning efficiency.
引用
收藏
页码:170 / 179
页数:10
相关论文
共 50 条
  • [31] Optimal No-Regret Learning in Repeated First-Price Auctions
    Han, Yanjun
    Weissman, Tsachy
    Zhou, Zhengyuan
    OPERATIONS RESEARCH, 2025, 73 (01)
  • [32] NO-REGRET NON-CONVEX ONLINE META-LEARNING
    Zhuang, Zhenxun
    Wang, Yunlong
    Yu, Kezi
    Lu, Songtao
    2020 IEEE INTERNATIONAL CONFERENCE ON ACOUSTICS, SPEECH, AND SIGNAL PROCESSING, 2020, : 3942 - 3946
  • [33] No-Regret Learning for Stackelberg Equilibrium Computation in Newsvendor Pricing Games
    Liu, Larkin
    Rong, Yuming
    ALGORITHMIC DECISION THEORY, ADT 2024, 2025, 15248 : 297 - 297
  • [34] Liquid Welfare Guarantees for No-Regret Learning in Sequential Budgeted Auctions
    Fikioris, Giannis
    Tardos, Eva
    MATHEMATICS OF OPERATIONS RESEARCH, 2024,
  • [35] Risk-Averse No-Regret Learning in Online Convex Games
    Wang, Zifan
    Shen, Yi
    Zavlanos, Michael M.
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162, 2022,
  • [36] Distributed No-Regret Learning for Stochastic Aggregative Games over Networks
    Lei, Jinlong
    Yi, Peng
    Li, Li
    2021 PROCEEDINGS OF THE 40TH CHINESE CONTROL CONFERENCE (CCC), 2021, : 7512 - 7519
  • [37] No-regret algorithms in on-line learning, games and convex optimization
    Sorin, Sylvain
    MATHEMATICAL PROGRAMMING, 2024, 203 (1-2) : 645 - 686
  • [38] No-Regret Learning in Bilateral Trade via Global Budget Balance
    Bernasconi, Martino
    Castiglioni, Matteo
    Celli, Andrea
    Fusco, Federico
    PROCEEDINGS OF THE 56TH ANNUAL ACM SYMPOSIUM ON THEORY OF COMPUTING, STOC 2024, 2024, : 247 - 258
  • [39] On the Convergence of No-Regret Learning Dynamics in Time-Varying Games
    Anagnostides, Ioannis
    Panageas, Ioannis
    Farina, Gabriele
    Sandholm, Tuomas
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 36 (NEURIPS 2023), 2023,
  • [40] No-Regret Distributed Learning in Subnetwork Zero-Sum Games
    Huang, Shijie
    Lei, Jinlong
    Hong, Yiguang
    Shanbhag, Uday V.
    Chen, Jie
    IEEE TRANSACTIONS ON AUTOMATIC CONTROL, 2024, 69 (10) : 6620 - 6635