Nr. | Issued | Question time | Deadline | Link | Additional Material |
1 | 16.10.2012 | 23.10.2012 | 30.10.2012 | Comparison of Optimization Algorithms | task1.zip |
2 | 16.10.2012 | 23.10.2012 | 30.10.2012 | Cart-Pole Controller Optimization | task2.zip |
3 | 16.10.2012 | 23.10.2012 | 30.10.2012 | Genetic Algorithms | |
4 | 6.11.2012 | 20.11.2012 | 27.11.2012 | Genetic Coding | |
5 | 6.11.2012 | 20.11.2012 | 27.11.2012 | RL theory I | MDP_Theory.pdf |
6 | 6.11.2012 | 20.11.2012 | 27.11.2012 | RL theory II | |
7 | 6.11.2012 | 20.11.2012 | 27.11.2012 | RL application: On- and off-policy learning | MountainCarDemo.zip |
8 | 6.11.2012 | 20.11.2012 | 27.11.2012 | RL game | |
9 | 4.12.2012 | 11.12.2012 | 15.1.2013 | Policy Gradient Methods: Swimmer | MLB_PolicyGradient.zip |
10 | 4.12.2012 | 11.12.2012 | 15.1.2013 | Bayesian networks | |
11 | 4.12.2012 | 11.12.2012 | 15.1.2013 | Approximate inference in Bayesian networks | Gibbs.zip |
12 | 15.1.2013 | 22.1.2013 | 5.2.2013 | Learning overhypotheses | |
13 | 15.1.2013 | 22.1.2013 | 5.2.2013 | Planning with approximate inference |
Practical | Date | Topic | Slides |
1 | 16.10.2012 | Organization and Search Algorithms | Slides (PDF) |
2 | 6.11.2012 | Reinforcement Learning | Slides (PDF) |
3 | 4.12.2012 | RL in Robotics and Probabilistic Inference | Slides (PDF) |
4 | 15.1.2013 | Learning and Planning with Probabilistic Inference | Slides (PDF) |