AnyMorph: Learning Transferable Polices By Inferring Agent Morphology

被引:0
作者
Trabucco, Brandon [1 ,2 ]
Phielipp, Mariano [2 ]
Berseth, Glen [3 ]
机构
[1] Carnegie Mellon Univ, Machine Learning Dept, Pittsburgh, PA 15213 USA
[2] Intel AI, San Diego, CA USA
[3] Mila, Montreal, PQ, Canada
来源
INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 162 | 2022年
关键词
D O I
暂无
中图分类号
TP18 [人工智能理论];
学科分类号
081104 ; 0812 ; 0835 ; 1405 ;
摘要
The prototypical approach to reinforcement learning involves training policies tailored to a particular agent from scratch for every new morphology. Recent work aims to eliminate the re-training of policies by investigating whether a morphology-agnostic policy, trained on a diverse set of agents with similar task objectives, can be transferred to new agents with unseen morphologies without re-training. This is a challenging problem that required previous approaches to use hand-designed descriptions of the new agent's morphology. Instead of hand-designing this description, we propose a data-driven method that learns a representation of morphology directly from the reinforcement learning objective. Ours is the first reinforcement learning algorithm that can train a policy to generalize to new agent morphologies without requiring a description of the agent's morphology in advance. We evaluate our approach on the standard benchmark for agent-agnostic control, and improve over the current state of the art in zero-shot generalization to new agents. Importantly, our method attains good performance without an explicit description of morphology.
引用
收藏
页数:15
相关论文
共 50 条
  • [31] Policy Stitching: Learning Transferable Robot Policies
    Jian, Pingcheng
    Lee, Easop
    Bell, Zachary
    Zavlanos, Michael M.
    Chen, Boyuan
    CONFERENCE ON ROBOT LEARNING, VOL 229, 2023, 229
  • [32] Inferring building height from footprint morphology data
    Stipek, Clinton
    Hauser, Taylor
    Adams, Daniel
    Epting, Justin
    Brelsford, Christa
    Moehl, Jessica
    Dias, Philipe
    Piburn, Jesse
    Stewart, Robert
    SCIENTIFIC REPORTS, 2024, 14 (01):
  • [33] Transferable empirical pseudopotenials from machine learning
    Kim, Rokyeon
    Son, Young -Woo
    PHYSICAL REVIEW B, 2024, 109 (04)
  • [34] Faster and transferable deep learning steganalysis on GPU
    Ye Dengpan
    Jiang Shunzhi
    Li Shiyu
    Liu ChangRui
    JOURNAL OF REAL-TIME IMAGE PROCESSING, 2019, 16 (03) : 623 - 633
  • [35] Learning Transferable UAV for Forest Visual Perception
    Chen, Lyujie
    Wang, Wufan
    Zhu, Jihong
    PROCEEDINGS OF THE TWENTY-SEVENTH INTERNATIONAL JOINT CONFERENCE ON ARTIFICIAL INTELLIGENCE, 2018, : 4883 - 4889
  • [36] Faster and transferable deep learning steganalysis on GPU
    Ye Dengpan
    Jiang Shunzhi
    Li Shiyu
    Liu ChangRui
    Journal of Real-Time Image Processing, 2019, 16 : 623 - 633
  • [37] Inferring paleohabitats from the functional morphology of bovid postcrania
    DeGusta, D
    JOURNAL OF HUMAN EVOLUTION, 2000, 38 (03) : A9 - A10
  • [38] Inferring Pyramidal Neuron Morphology using EAP Data
    Chen, Ziao
    Carroll, Matthew
    Nair, Satish S.
    2023 11TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING, NER, 2023,
  • [39] INFERRING SEISMIC BEHAVIOR FROM MORPHOLOGY IN TIMBER ROOFS
    Parisi, Maria Adelaide
    Chesi, Claudio
    Tardini, Chiara
    INTERNATIONAL JOURNAL OF ARCHITECTURAL HERITAGE, 2012, 6 (01) : 100 - 116
  • [40] Inferring behavior from pedal phalangeal morphology in theropods
    Kambic, Robert
    JOURNAL OF VERTEBRATE PALEONTOLOGY, 2007, 27 (03) : 97A - 97A