English

If sufficient demand

To become familiar with reinforcement learning.

- Markov Decision Processes
- Dynamic programming
- Iterative policy evaluation
- Iterative policy iteration
- Value iteration
- Model-free planning
- Monte-Carlo methods
- Model-free control
- Value Function Approximation
- Policy Gradient Methods
- Exploration and Exploitation

- understand the basic concepts and methods of reinforcement learning

- be able to understand the implementation of reinforcement learning using Python and Tensorflow

- understand for which problems reinforcement learning is suitable

Seminars

Exercises

Self-study literature review

Miscellaneous

Based on the Reinforcement Learning Course given by David Silver at UCL and the associated video presentations.

Miscellaneous

Sufficient active participation in the course meetings

Failed, pass

Admitted to PhD program at an engineering faculty

None

None

 

The course is based on video lectures by David Silver.

FRT205F

2019-09-12

Professor Thomas Johansson