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
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] Learning Fair and Transferable Representations with Theoretical Guarantees
    Oneto, Luca
    Donini, Michele
    Pontil, Massimiliano
    Maurer, Andreas
    2020 IEEE 7TH INTERNATIONAL CONFERENCE ON DATA SCIENCE AND ADVANCED ANALYTICS (DSAA 2020), 2020, : 30 - 39
  • [32] Inferring diet from dental morphology in terrestrial mammals
    Pineda-Munoz, Silvia
    Lazagabaster, Ignacio A.
    Alroy, John
    Evans, Alistair R.
    METHODS IN ECOLOGY AND EVOLUTION, 2017, 8 (04): : 481 - 491
  • [33] The integrative approach to inferring homology: morphology and development combined
    Arsham Nejad Kourki
    Biology & Philosophy, 2022, 37
  • [34] Inferring the morphology of the Galactic Center excess with Gaussian processes
    Ramirez, Edward D.
    Sun, Yitian
    Buckley, Matthew R.
    Mishra-Sharma, Siddharth
    Slatyer, Tracy R.
    PHYSICAL REVIEW D, 2025, 111 (06)
  • [36] Inferring Morphology of a Neuron from In Vivo LFP Data
    Chen, Ziao
    Dopp, Dan
    Headley, Drew B.
    Nair, Satish S.
    2021 10TH INTERNATIONAL IEEE/EMBS CONFERENCE ON NEURAL ENGINEERING (NER), 2021, : 774 - 777
  • [37] 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
  • [38] 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
  • [39] 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
  • [40] Transferable Dictionary Learning Fused Data Augmentation
    Wang, Ziru
    Li, Zhenmin
    Computer Engineering and Applications, 2024, 57 (23) : 193 - 199