Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

    Abstract

    Creating open-ended algorithms, which generate their own never-ending stream of novel and appropriately challenging learning opportunities, could help to automate and accelerate progress in machine learning. A recent step in this direction is the Paired Open-Ended Trailblazer (POET), an algorithm that generates and solves its own challenges, and allows solutions to goal-switch between challenges to avoid local optima. However, the original POET was unable to demonstrate its full creative potential because of limitations of the algorithm itself and because of external issues including a limited problem space and lack of a universal progress measure. Importantly, both limitations pose impediments not only for POET, but for the pursuit of open-endedness in general. Here we introduce and empirically validate two new innovations to the original algorithm, as well as two external innovations designed to help elucidate its full potential. Together, these four advances enable the most open-ended algorithmic demonstration to date. The algorithmic innovations are (1) a domain-general measure of how meaningfully novel new challenges are, enabling the system to potentially create and solve interesting challenges endlessly, and (2) an efficient heuristic for determining when agents should goal-switch from one problem to another (helping open-ended search better scale). Outside the algorithm itself, to enable a more definitive demonstration of open-endedness, we introduce (3) a novel, more flexible way to encode environmental challenges, and (4) a generic measure of the extent to which a system continues to exhibit open-ended innovation. Enhanced POET produces a diverse range of sophisticated behaviors that solve a wide range of environmental challenges, many of which cannot be solved through other means.

    Authors

    Rui Wang, Joel Lehman, Aditya Rawal, Jiale Zhi, Yulun Li, Jeff Clune, Kenneth O. Stanley

    Publication

    37th International Conference on Machine Learning (ICML), 2020

    Full Paper

    Enhanced POET: Open-Ended Reinforcement Learning through Unbounded Invention of Learning Challenges and their Solutions

    Comments
    Previous articleHeterogeneous Causal Learning for Effectiveness Optimization in User Marketing
    Next articleEstimating Q(s,s’) with Deep Deterministic Dynamics Gradients
    Rui Wang
    Rui Wang is a senior research scientist with Uber AI. He is passionate about advancing the state of the art of machine learning and AI, and connecting cutting-edge advances to the broader business and products at Uber. His recent work at Uber was published on leading international conferences in machine learning and AI (ICML, IJCAI, GECCO, etc.), won a Best Paper Award at GECCO 2019, and was covered by technology media such as Science, Wired, VentureBeat, and Quanta Magazine.
    Joel Lehman
    Joel Lehman was previously an assistant professor at the IT University of Copenhagen, and researches neural networks, evolutionary algorithms, and reinforcement learning.
    Aditya Rawal
    Aditya Rawal is a research scientist at Uber AI Labs. His interests lies at the convergence of two research fields - neuroevolution and deep learning. His belief is that evolutionary search can replace human ingenuity in creating next generation of deep networks. Previously, Aditya received his MS/PhD in Computer Science from University of Texas at Austin, advised by Prof. Risto Miikkulainen. During his PhD, he developed neuroevolution algorithms to evolve recurrent architectures for sequence-prediction problems and construct multi-agent systems that cooperate, compete and communicate.
    Jiale Zhi
    Jiale Zhi is a senior software engineer with Uber AI. His area of interest is distributed computing, big data, scientific computation, evolutionary computing, and reinforcement learning. He is also interested in real-world applications of machine learning in traditional software engineering. He is the creator of the Fiber project, a scalable, distributed framework for large scale parallel computation applications. Before Uber AI, he was a Tech Lead in Uber's edge team, which manages Uber's global mobile network traffic and routing.
    Yulun Li
    Yulun Li previously worked as a software engineer with Uber AI.
    Jeff Clune
    Jeff Clune is the former Loy and Edith Harris Associate Professor in Computer Science at the University of Wyoming, a Senior Research Manager and founding member of Uber AI Labs, and currently a Research Team Leader at OpenAI. Jeff focuses on robotics and training neural networks via deep learning and deep reinforcement learning. He has also researched open questions in evolutionary biology using computational models of evolution, including studying the evolutionary origins of modularity, hierarchy, and evolvability. Prior to becoming a professor, he was a Research Scientist at Cornell University, received a PhD in computer science and an MA in philosophy from Michigan State University, and received a BA in philosophy from the University of Michigan. More about Jeff’s research can be found at JeffClune.com
    Kenneth O. Stanley
    Before joining Uber AI Labs full time, Ken was an associate professor of computer science at the University of Central Florida (he is currently on leave). He is a leader in neuroevolution (combining neural networks with evolutionary techniques), where he helped invent prominent algorithms such as NEAT, CPPNs, HyperNEAT, and novelty search. His ideas have also reached a broader audience through the recent popular science book, Why Greatness Cannot Be Planned: The Myth of the Objective.