Cart-Pole Reinforcement Learning
Balancing a typical inverted pendulum with Temporal Difference methods. Done as a personal hobby project. Controlled with a Raspberry Pi 1B using I2C interface. There is no x-position state sensing - the cart was smashing L/R end stops (and failing the episode), yet it eventually learns to throttle down such movements.
I used these ICs to control stepper:
- NXP PCA9629A
- TI DRV8825
Unfortunately the motor (pulled from my 3D printer) is not powerful enough for auto pole swing-up even with trajectory energy shaping methods.
Видео Cart-Pole Reinforcement Learning канала Cheng-Yueh Liu
I used these ICs to control stepper:
- NXP PCA9629A
- TI DRV8825
Unfortunately the motor (pulled from my 3D printer) is not powerful enough for auto pole swing-up even with trajectory energy shaping methods.
Видео Cart-Pole Reinforcement Learning канала Cheng-Yueh Liu
Показать
Комментарии отсутствуют
Информация о видео
Другие видео канала
Learning to Swing-Up and Balance from ScratchControl of a Quadrotor with Reinforcement LearningInverted pendulum on a cart3A95.50 Double Pendulum Ring and BarWhat is Artificial Intelligence? In 5 minutes.Projects In Machine Learning | Cart And Pole Balancing Problem With The Open AI Gym | EduonixSocially Aware Motion Planning with Deep Reinforcement LearningCart Pendulum ModelReinforcement Learning Simulation - Cart-Pole (Inverted Pendulum) TaskAlphaGo - The Movie | Full award-winning documentaryIllustrated Guide to Recurrent Neural Networks: Understanding the IntuitionHill Climbing Algorithm balances a Cart PoleA New Take on the Inverted Pendulum RobotRL Course by David Silver - Lecture 2: Markov Decision ProcessMarI/O - Machine Learning for Video GamesIntro - Training a neural network to play a game with TensorFlow and Open AIRotary Inverted Pendulum System Using Reinforcement LearningReinforcement Learning on Real-World Two-Wheeled RobotSwing-up and Control of Linear Triple Inverted PendulumSelf-Balancing Inverted Pendulum Robot Demo