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
  • [21] Learning Indistinguishable and Transferable Adversarial Examples
    Zhang, Wu
    Zou, Junhua
    Duan, Yexin
    Zhou, Xingyu
    Pan, Zhisong
    PATTERN RECOGNITION AND COMPUTER VISION, PT IV, 2021, 13022 : 152 - 164
  • [22] Learning Adversarially Fair and Transferable Representations
    Madras, David
    Creager, Elliot
    Pitassi, Toniann
    Zemel, Richard
    INTERNATIONAL CONFERENCE ON MACHINE LEARNING, VOL 80, 2018, 80
  • [23] Fuzzy inferring mathematical morphology and optical implementation
    Liu, L
    OPTICAL ENGINEERING, 1996, 35 (10) : 2912 - 2920
  • [24] Transferable Deep Metric Learning for Clustering
    Chehboune, Mohamed Alami
    Kaddah, Rim
    Read, Jesse
    ADVANCES IN INTELLIGENT DATA ANALYSIS XXI, IDA 2023, 2023, 13876 : 15 - 28
  • [25] Learning and inferring mransportation routines
    Liao, L
    Fox, D
    Kautz, H
    PROCEEDING OF THE NINETEENTH NATIONAL CONFERENCE ON ARTIFICIAL INTELLIGENCE AND THE SIXTEENTH CONFERENCE ON INNOVATIVE APPLICATIONS OF ARTIFICIAL INTELLIGENCE, 2004, : 348 - 353
  • [26] Modeling Learning of Derivation Morphology in a Multi-Agent Simulation.
    Pustylnikov, Olga
    2009 AFRICON, VOLS 1 AND 2, 2009, : 789 - 794
  • [27] Learning and inferring transportation routines
    Liao, Lin
    Patterson, Donald J.
    Fox, Dieter
    Kautz, Henry
    ARTIFICIAL INTELLIGENCE, 2007, 171 (5-6) : 311 - 331
  • [28] Learning Transferable Domain Priors for Safe Exploration in Reinforcement Learning
    Karimpanal, Thommen George
    Rana, Santu
    Gupta, Sunil
    Truyen Tran
    Venkatesh, Svetha
    2020 INTERNATIONAL JOINT CONFERENCE ON NEURAL NETWORKS (IJCNN), 2020,
  • [29] Transferable Adversarial Defense by Fusing Reconstruction Learning and Denoising Learning
    Gao, Song
    Yao, Shaowen
    Li, Ruidong
    IEEE CONFERENCE ON COMPUTER COMMUNICATIONS WORKSHOPS (IEEE INFOCOM WKSHPS 2021), 2021,
  • [30] Transferable empirical pseudopotenials from machine learning
    Kim, Rokyeon
    Son, Young -Woo
    PHYSICAL REVIEW B, 2024, 109 (04)