OpenAI Gym is an open-source Python library that provides standardized environments to make the development and testing of reinforcement learning algorithms fast and reproducible. With this library, users can train AI to do everything from solving simple classical control problems to playing Atari games at an expert level. Best of all, by providing predesigned environments for training, compatibility with powerful libraries like KerasRL, and built-in rendering capabilities, Gym makes it easier than ever before to get started with reinforcement learning.
This presentation will show how someone with little or no previous experience applying reinforcement learning can get a project off the ground using OpenAI Gym. It will walk through the basic functionality of the library, and demonstrate how to design, train, and analyze the performance of learners. Along the way, it will clarify some of the key concepts, best practices, and pitfalls of reinforcement learning. By the end of the presentation, attendees will have everything they need to start their reinforcement learning journey.
Anthony Melson is an entrepreneur, data scientist, and community builder. He has experience deploying python-based machine learning solutions to solve problems in marketing, risk assessment, and customer relations, and regularly gives talks and guest lectures on ML in the Saint Louis area. He is currently the general manager of Melson Bonding (a company he founded in 2008) and co-organizer of the Saint Louis Machine Learning and Data Science group.