TinyRL: Teaching AI to Swing Up a Real Pendulum

TinyRL: Teaching AI to Swing Up a Real Pendulum

Digi-Key via YouTube Direct link

- Test agent on the pendulum

14 of 15

14 of 15

- Test agent on the pendulum

Class Central Classrooms beta

YouTube videos curated by Class Central.

Classroom Contents

TinyRL: Teaching AI to Swing Up a Real Pendulum

Automatically move to the next video in the Classroom when playback concludes

  1. 1 - Introduction
  2. 2 - Hardware overview
  3. 3 - Modifying the pendulum tower
  4. 4 - Arduino communication interface
  5. 5 - Overview of reinforcement learning
  6. 6 - Reward function
  7. 7 - Agent actor-critic deep neural network
  8. 8 - Hyperparameter optimization overview
  9. 9 - Agent training with Python
  10. 10 - Troubleshooting an agent that does not learn
  11. 11 - Reduce scope to just swing up and use discrete action space
  12. 12 - Train simpler agent
  13. 13 - Deploy agent to ESP32
  14. 14 - Test agent on the pendulum
  15. 15 - Conclusion and further areas of research

Never Stop Learning.

Get personalized course recommendations, track subjects and courses with reminders, and more.

Someone learning on their laptop while sitting on the floor.