Paired Open-Ended Trailblazer (POET): Endlessly Generating Increasingly Complex and Diverse Learning Environments and Their Solutions
Rui Wang, Joel Lehman, Jeff Clune, Kenneth O. Stanley

TL;DR
POET is an algorithm that simultaneously generates diverse, increasingly complex environments and optimizes agents to solve them, fostering open-ended discovery and innovation in machine learning.
Contribution
The paper introduces POET, a novel method for co-evolving environments and agents, enabling continuous open-ended learning and transfer of solutions across challenges.
Findings
POET produces diverse, sophisticated behaviors solving complex challenges.
Solution transfer accelerates learning and fosters innovation.
POET outperforms direct optimization and curriculum methods.
Abstract
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. Such a process would in effect build its own diverse and expanding curricula, and the solutions to problems at various stages would become stepping stones towards solving even more challenging problems later in the process. The Paired Open-Ended Trailblazer (POET) algorithm introduced in this paper does just that: it pairs the generation of environmental challenges and the optimization of agents to solve those challenges. It simultaneously explores many different paths through the space of possible problems and solutions and, critically, allows these stepping-stone solutions to transfer between problems if…
Peer Reviews
No public reviews on file for this paper yet. If you reviewed it on a platform where reviews are public (OpenReview, ICLR, NeurIPS, ICML), you can paste yours below so the community can read it here.
Code & Models
Videos
POET: Endlessly Generating Increasingly Complex and Diverse Learning Environments and Solutions· youtube
Don't invent faster horses - Prof. Jeff Clune· youtube
POET: Paired Open-Ended Trailblazer | Paper Explained· youtube
Taxonomy
TopicsReinforcement Learning in Robotics · Machine Learning and Algorithms · Data Stream Mining Techniques
