Corpus ID: 208139268

Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning

@article{Luck2019DataefficientCO,
  title={Data-efficient Co-Adaptation of Morphology and Behaviour with Deep Reinforcement Learning},
  author={Kevin Sebastian Luck and Heni Ben Amor and Roberto Calandra},
  journal={ArXiv},
  year={2019},
  volume={abs/1911.06832}
}
  • Kevin Sebastian Luck, Heni Ben Amor, Roberto Calandra
  • Published in ArXiv 2019
  • Mathematics, Computer Science
  • Humans and animals are capable of quickly learning new behaviours to solve new tasks. Yet, we often forget that they also rely on a highly specialized morphology that co-adapted with motor control throughout thousands of years. Although compelling, the idea of co-adapting morphology and behaviours in robots is often unfeasible because of the long manufacturing times, and the need to re-design an appropriate controller for each morphology. In this paper, we propose a novel approach to… CONTINUE READING

    Create an AI-powered research feed to stay up to date with new papers like this posted to ArXiv

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 25 REFERENCES

    Pybullet, a python module for physics simulation for games, robotics and machine learning

    • E. Coumans, Y. Bai
    • 2019
    VIEW 8 EXCERPTS
    HIGHLY INFLUENTIAL

    Reinforcement Learning for Improving Agent Design

    • David Ha
    • Computer Science, Mathematics, Medicine
    • Artificial Life
    • 2018
    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Adapting arbitrary normal mutation distributions in evolution strategies: the covariance matrix adaptation

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Particle Swarm Optimization for Single Objective Continuous Space Problems: A Review

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    A new optimizer using particle swarm theory

    VIEW 5 EXCERPTS
    HIGHLY INFLUENTIAL

    Data-efficient Learning of Morphology and Controller for a Microrobot

    VIEW 2 EXCERPTS

    Hebi robotics x-series hexapod data sheet

    • HEBI Robotics
    • http://docs.hebi.us/ resources/kits/assyInstructions/A-2049-01_Data_Sheet.pdf
    • 2019
    VIEW 1 EXCERPT

    Jointly Learning to Construct and Control Agents using Deep Reinforcement Learning

    VIEW 3 EXCERPTS