Corpus ID: 57573844

Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions

@article{Wang2019PairedOT,
  title={Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions},
  author={Rui Wang and Joel Lehman and Jeff Clune and Kenneth O. Stanley},
  journal={ArXiv},
  year={2019},
  volume={abs/1901.01753}
}
  • Rui Wang, Joel Lehman, +1 author Kenneth O. Stanley
  • Published 2019
  • Computer Science
  • ArXiv
  • While the history of machine learning so far largely encompasses a series of problems posed by researchers and algorithms that learn their solutions, an important question is whether the problems themselves can be generated by the algorithm at the same time as they are being solved. [...] Key Result Our results show that POET produces a diverse range of sophisticated behaviors that solve a wide range of environmental challenges, many of which cannot be solved by direct optimization alone, or even through a…Expand Abstract

    Figures, Tables, and Topics from this paper.

    Citations

    Publications citing this paper.
    SHOWING 1-10 OF 49 CITATIONS

    Why Open-Endedness Matters

    VIEW 2 EXCERPTS
    CITES BACKGROUND

    GENERATE SYNTHETIC TRAINING DATA

    • 2019
    VIEW 6 EXCERPTS
    CITES BACKGROUND & METHODS
    HIGHLY INFLUENCED

    FILTER CITATIONS BY YEAR

    2018
    2020

    CITATION STATISTICS

    • 4 Highly Influenced Citations

    • Averaged 16 Citations per year from 2018 through 2020

    • 40% Increase in citations per year in 2020 over 2019

    References

    Publications referenced by this paper.
    SHOWING 1-10 OF 89 REFERENCES

    Episodic Curiosity through Reachability

    VIEW 1 EXCERPT

    Teacher-Student Curriculum Learning

    Mastering the game of Go without human knowledge

    VIEW 2 EXCERPTS