Reinforcement learning
Markov decision processes, Q-learning, policy gradient
Also known as: Markov Decision Processes
4 lecture recordings, about 18 hours
Lecture recordings
- Stanford — Stanford CS224R Deep Reinforcement Learning, 19 lectures
- Прочие каналы — DeepMind x UCL | Deep Learning Lecture Series 2021, 13 lectures
- Прочие каналы — Reinforcement Learning Tutorials, 14 lectures
- Прочие каналы — DeepMind x UCL | Introduction to Reinforcement Learning 2015, 10 lectures
- Прочие каналы — Gymnasium (Deep) Reinforcement Learning Tutorials, 11 lectures
What you need first
Field of knowledge
The map of knowledge