DigiKey, the global distribution leader of electronic components and automation products, is hosting a webinar with Shawn Hymel: “Train a balance bot with reinforcement learning,” scheduled for Thursday, Aug. 13, 2026, at 10 a.m. CDT. The free 90 minute virtual event will be a hands-on robotics and AI workshop that will teach attendees how to get started in the growing field of reinforcement learning (RL).
Reinforcement learning is a powerful domain within machine learning that teaches agents to make decisions by interacting with an environment and maximizing a reward signal. It can enable robots to learn complex behaviors like balancing, walking and recovering from falls entirely in simulation before ever touching real hardware.
During the workshop, Hymel will guide attendees through training a self-balancing robot using RL and deploying it on real hardware. Attendees will learn to:
- Import a 3D model of the M5Stack Bala-C into the MuJoCo physics simulator
- Train a neural network policy using a multi-phase PPO curriculum
- Deploy the trained actor network to an ESP32 microcontroller using Arduino
- Understand the sim-to-real pipeline, a foundational skill for applying modern AI
techniques to physical robotics
“Reinforcement learning has quickly become an exciting tool across a wide range of modern applications,” said David Sandys, senior director of technical enablement & engagement for DigiKey. “It’s a complex and growing field, and knowing where to begin can be tricky. That’s why we’re thankful to partner with Shawn Hymel to help bring this educational workshop to our customers and community to share how to get started, and why it’s beneficial to gain this knowledge.”
“Almost every major robotics lab has turned to reinforcement learning to build robust, AI-powered control and decision-making for their robots, from quadrupeds to bipeds,” says Hymel, expert instructor and content creator. “However, RL remains hard to approach. Training a policy can take millions of simulation steps, and getting the reward function right is as much art as science. This webinar will help lower the barrier to entry for anyone who wants to build their own robots with RL.”
Anyone who would like to follow along with the webinar is encouraged to have either the M5Stack Bala-C Balance Bot or the M5Stack Bala2 Fire Self-Balancing Robot. If you can’t attend the live webinar, you’re still encouraged to register, and the recording will be sent to all registrants following the event. Everyone is welcome to register for free.
DigiKey has also debuted the first of a six-part educational YouTube series in partnership with Hymel, designed to help engineers, hobbyists and students get started with robotics and RL. The full series will walk viewers through training a robot using modern RL techniques, from simulation to hardware deployment. By the end of the series, viewers will have a working remote-controlled balance bot that learned its own control policy, entirely through trial and error in simulation. Viewers can also follow the full write-up of the tutorial on DigiKey’s Maker.io site.
This webinar and video series furthers DigiKey’s commitment to providing helpful resources and education for engineers, designers, makers and students. For more information about other resources and educational content, please visit DigiKey.com.
