Reinforcement Learning - MIT 6.S191 Lecture 5

Explore deep reinforcement learning in this comprehensive lecture from MIT's Introduction to Deep Learning course. Delve into various aspects of reinforcement learning, including classes of learning problems, key definitions, Q functions, and Deep Q Networks. Examine Atari game results and limitations, policy learning algorithms, and the differences between discrete and continuous actions. Learn about training policy gradients and real-life applications of reinforcement learning, including the VISTA simulator. Discover breakthrough achievements like AlphaGo, AlphaZero, and MuZero. Gain a solid understanding of reinforcement learning concepts and their practical applications in this hour-long session led by Alexander Amini.

- Introduction
- Classes of learning problems
- Definitions
- The Q function
- Deeper into the Q function
- Deep Q Networks
- Atari results and limitations
- Policy learning algorithms
- Discrete vs continuous actions
- Training policy gradients
- RL in real life
- VISTA simulator
- AlphaGo and AlphaZero and MuZero
- Summary