arrow_back Back home

2 July 2023

Summer games

Game of Life

Policy gradient RL on an inverted pendulum

Model at start of training

Model after 500 episodes

Notes from MIT Deep Learning 6.S191

Course link

• Lecture 1: Foundations
• Lecture 2: Recurrent Neural Networks
• Lecture 3: Convolutional Neural Networks
• Lecture 7: Limitations
• Lecture 10: Robot learning