Hearts Gym: Learning Reinforcement Learning as a Team Event
This work addresses the problem of engaging students in online RL education for data science graduate programs, though it is incremental as it builds on existing teaching methods with a specific game-based environment.
The authors tackled the challenge of teaching Reinforcement Learning (RL) during the COVID-19 pandemic by organizing a graduate course with a competitive team-based approach, using a custom RL environment called Hearts Gym for hands-on practice, and qualitatively evaluated the course as an exciting learning experience.
Amidst the COVID-19 pandemic, the authors of this paper organized a Reinforcement Learning (RL) course for a graduate school in the field of data science. We describe the strategy and materials for creating an exciting learning experience despite the ubiquitous Zoom fatigue and evaluate the course qualitatively. The key organizational features are a focus on a competitive hands-on setting in teams, supported by a minimum of lectures providing the essential background on RL. The practical part of the course revolved around Hearts Gym, an RL environment for the card game Hearts that we developed as an entry-level tutorial to RL. Participants were tasked with training agents to explore reward shaping and other RL hyperparameters. For a final evaluation, the agents of the participants competed against each other.