Nr. | Issued | Question time | Deadline | Assignment | Additional Material |
1 | 14.10.2014 | 21.10.2014 | 28.10.2014 | Comparison of Optimization Algorithms | task1.zip |
2 | 14.10.2014 | 21.10.2014 | 28.10.2014 | Cart-Pole Controller Optimization | task2.zip |
3 | 14.10.2014 | 21.10.2014 | 28.10.2014 | Genetic Algorithm | |
4 | 04.11.2014 | 11.11.2014 | 18.11.2014 | RL theory I | MDP_Theory.pdf |
5 | 04.11.2014 | 11.11.2014 | 18.11.2014 | RL theory II | |
6 | 04.11.2014 | 11.11.2014 | 18.11.2014 | RL application: On- and off-policy learning | MountainCarDemo.zip |
7 | 04.11.2014 | 11.11.2014 | 18.11.2014 | RL game | |
8 | 09.12.2014 | 16.12.2014 | 13.01.2015 | Policy Gradient Methods | PolicyGradient.zip |
9 | 09.12.2014 | 16.12.2014 | 13.01.2015 | Bayesian networks | |
10 | 09.12.2014 | 16.12.2014 | 13.01.2015 | Approximate inference in Bayesian networks | Gibbs.zip |
11 | 20.01.2015 | 27.01.2015 | 03.02.2015 | Learning overhypotheses |
Practical | Date | Topic |
1 | 14.10.2014 | Organization and Search Algorithms |
2 | 04.11.2014 | Reinforcement Learning |
3 | 09.12.2014 | RL in Robotics and Probabilistic Inference |
4 | 20.01.2015 | Learning with Probabilistic Inference |