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

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 better, catalyzing innovation. The term open-ended signifies the intriguing potential for algorithms like POET to continue to create novel and increasingly complex capabilities without bound. 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 direct-path curriculum-building control algorithm introduced to highlight the critical role of open-endedness in solving ambitious challenges. The ability to transfer solutions from one environment to another proves essential to unlocking the full potential of the system as a whole, demonstrating the unpredictable nature of fortuitous stepping stones. We hope that POET will inspire a new push towards open-ended discovery across many domains, where algorithms like POET can blaze a trail through their interesting possible manifestations and solutions.

28 pages, 9 figures

References in corpus (4)

• Robots that can adapt like animals
• Emergence of Locomotion Behaviours in Rich Environments
• Illuminating search spaces by mapping elites
• On the Relationship Between the OpenAI Evolution Strategy and Stochastic Gradient Descent

Cited by in corpus (8)

• Generative Teaching Networks: Accelerating Neural Architecture Search by Learning to Generate Synthetic Training Data
• Open-ended Learning in Symmetric Zero-sum Games
• Teacher algorithms for curriculum learning of Deep RL in continuously parameterized environments
• BADGER: Learning to (Learn [Learning Algorithms] through Multi-Agent Communication)
• On the Measure of Intelligence
• Curriculum in Gradient-Based Meta-Reinforcement Learning
• Toybox: A Suite of Environments for Experimental Evaluation of Deep Reinforcement Learning
• A Markov Decision Process Approach to Active Meta Learning