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
  • [11] Learning Transferable Graph Exploration
    Dai, Hanjun
    Li, Yujia
    Wang, Chenglong
    Singh, Rishabh
    Huang, Po-Sen
    Kohli, Pushmeet
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 32 (NIPS 2019), 2019, 32
  • [12] Learning Transferable Adversarial Perturbations
    Nakka, Krishna Kanth
    Salzmann, Mathieu
    ADVANCES IN NEURAL INFORMATION PROCESSING SYSTEMS 34 (NEURIPS 2021), 2021, 34
  • [13] Transferable Graph Neural Networks for Inferring Road Type Attributes in Street Networks
    Iddianozie, Chidubem
    Mcardle, Gavin
    IEEE ACCESS, 2021, 9 : 158331 - 158339
  • [14] PROFESSIONALS AND ANTINEOPLASTIC AGENT POLICES IN THE PUBLIC HEALTH SERVICE IN ROSARIO: QUALITATIVE STUDY
    Palchik, Valeria
    Traverso, Maria L.
    Colautti, Marisel
    Bianchi, Mariela
    Dolza, Maria L.
    Catena, Jose M.
    Hernandez, Valeria
    Salamano, Mercedes
    REVISTA DE SALUD PUBLICA-CORDOBA, 2018, 22 (01): : 31 - 40
  • [15] The Body is Not a Given: Joint Agent Policy Learning and Morphology Evolution
    Banarse, Dylan
    Bachrach, Yoram
    Liu, Siqi
    Lever, Guy
    Heess, Nicolas
    Fernando, Chrisantha
    Kohli, Pushmeet
    Graepel, Thore
    AAMAS '19: PROCEEDINGS OF THE 18TH INTERNATIONAL CONFERENCE ON AUTONOMOUS AGENTS AND MULTIAGENT SYSTEMS, 2019, : 1134 - 1142
  • [16] Provably Efficient Learning of Transferable Rewards
    Metelli, Alberto Maria
    Ramponi, Giorgia
    Concetti, Alessandro
    Restelli, Marcello
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 139, 2021, 139
  • [17] Transferable Meta Learning Across Domains
    Kang, Bingyi
    Feng, Jiashi
    UNCERTAINTY IN ARTIFICIAL INTELLIGENCE, 2018, : 177 - 187
  • [18] Transferable regularization and normalization: Towards transferable feature learning for unsupervised domain adaptation
    Zhang, Changchun
    Zhang, Junguo
    INFORMATION SCIENCES, 2022, 609 : 595 - 604
  • [19] Learning Transferable Perturbations for Image Captioning
    Wu, Hanjie
    Liu, Yongtuo
    Cai, Hongmin
    He, Shengfeng
    ACM Transactions on Multimedia Computing, Communications and Applications, 2022, 18 (02)
  • [20] Online deep transferable dictionary learning
    Wu, Sheng
    Wu, Ancong
    Zheng, Wei-Shi
    PATTERN RECOGNITION, 2021, 118