![](https://ccweb.imgix.net/https%3A%2F%2Fwww.classcentral.com%2Fimages%2Ficon-black-friday.png?auto=format&ixlib=php-4.1.0&s=fe56b83c82babb2f8fce47a2aed2f85d)
Overview
![](https://ccweb.imgix.net/https%3A%2F%2Fwww.classcentral.com%2Fimages%2Ficon-black-friday.png?auto=format&ixlib=php-4.1.0&s=fe56b83c82babb2f8fce47a2aed2f85d)
This course teaches a new framework in reinforcement learning that enables agents to transfer knowledge from previous tasks to solve new tasks efficiently. The course covers topics such as Q-Learning, multiple rewards and policies, successor features, zero-shot policy for new tasks, and more. The teaching method includes lectures on problem statements, examples, and results, with a focus on reducing data requirements in reinforcement learning. The course is intended for individuals interested in AI, research, and reinforcement learning, looking to enhance their understanding of policy updates in RL algorithms.
Syllabus
- Intro & Overview
- Problem Statement
- Q-Learning Primer
- Multiple Rewards, Multiple Policies
- Example Environment
- Tasks as Linear Mixtures of Features
- Successor Features
- Zero-Shot Policy for New Tasks
- Results on New Task W3
- Inferring the Task via Regression
- The Influence of the Given Policies
- Learning the Feature Functions
- More Complicated Tasks
- Life-Long Learning, Comments & Conclusion
Taught by
Yannic Kilcher