The seminar topic selection aims to cover some of the most fundamental model-free and model-based deep reinforcement learning algorithms and give some insight into one additional key topic in deep reinforcement learning, namely methods for improving exploration. You are more than welcome to use additional resources/materials for preparing your talk. The (bracketed notes) refer to specific sections in the book which should serve as a good starting point. Monte Carlo Methods (5.1, 5.2, 5.3) and Temporal Difference Methods (6.1, 6.2) Multi-armed bandits & Markov Decision Processes (2.1, 3)Ĥ.
The proseminar topics are largely based on the RL book by Sutton & Barto.ġ.
