Nr.  Issued  Question time  Deadline  Link  Additional Material 
1  19.10.2010    2.11.2010  Comparison of Optimization Algorithms 
task1.zip 
2  19.10.2010    2.11.2010  CartPole Controller Optimization 
task2.zip 
3  19.10.2010    2.11.2010  Genetic Algorithms 

4  9.11.2010  16.11.2010  23.11.2010  RL theory I 
MDP_Theory.pdf

5  9.11.2010  16.11.2010  23.11.2010  RL theory II 

6  9.11.2010  16.11.2010  23.11.2010  RL application I: On and offpolicy learning 
MountainCarDemo.zip

7  9.11.2010  16.11.2010  23.11.2010  RL application II: Function approximation 
CartPoleDemo.zip

8  9.11.2010  16.11.2010  23.11.2010  RL application III: Selfplay 

9  30.11.2010  14.12.2010  11.1.2011  Policy Gradient Methods: Swimmer 
MLB_PolicyGradient.zip

10  30.11.2010  14.12.2010  11.1.2011  Reward Weighted Regression: Cannon Warfare 
cannon.zip

11  30.11.2010  14.12.2010  11.1.2011  Bayesian networks 

12  30.11.2010  14.12.2010  11.1.2011  Approximate inference in Bayesian networks 
Gibbs.zip

13  25.1.2011    22.2.2011  Learning overhypotheses 

14  25.1.2011    22.2.2011  Planning with Approximate Inference 
