Next:
Exercises
Machine Learning B
708.062 10W 1sst KU, WS 2010/11
Exercises
Comparison of Optimization Algorithms [5 P]
Cart-Pole Controller Optimization [5 P]
Genetic Algorithm [3* P]
RL theory I [3 P]
RL theory II [3 P]
RL application I: On- and off-policy learning [3 P]
RL application II: Function approximation [3 P]
RL application III: Self-play [3* P]
Policy Gradient Methods: Swimmer [3+1* P]
Matlab package Description
Policy Gradient Methods
Reward Weighted Regression: Cannon Warfare [3 P]
Bayesian networks [1+1* P]
Approximate inference in Bayesian networks [3 P]
Learning overhypotheses [3 P]
Planning with Approximate Inference [3* P]
Task Space Planning
Task Space Planning with Obstacle Avoidance
Pseudo-Dynamic Planning with Obstacle Avoidance (Optional Task)
About this document ...
Haeusler Stefan 2011-01-25