English

If sufficient demand

To teach the participants basic topics in deep reinforcement learning

Q functions, Advanced Policy Gradients, Model Based planning, Model Based RL, Model Based Policy Learning, Control as Inference, Inverse Reinforcement Learning, Distributed RL, Challenges and Open problems

understand advanced topics in reinforcement learning and implementation aspects of deep reinforcement learning using neural networks.

be able to implement different deep reinforcement learning techniques based on Neural Networks.

understand the advantages and drawbacks of application of reinforcement learning techniques.
be able to select a good learning environment for effective reinforcement learning.

Seminars

Exercises

Self-study literature review

Miscellaneous

based on Berkely deep RL course "CS285" and a few assignments available on Github

Miscellaneous

Active participation in the course

Failed, pass

Admitted to PhD program at an engineering faculty

Basic reinforcement learning knowledge, basic neural network construction and training using tensorflow or pytorch

None

Sutton, Richard S. & Barto, Andrew G.: Reinforcement Learning, Second Edition. ISBN 9780262039246.

FRT240F

2021-02-18

Professor Thomas Johansson