will be places of discussion where the current topic is summarized by
the lecturer and discussed among all present. The students are expected
to prepare by reading given material in advance prior to each lecture.
Course lectures will be given during first period on Wednesdays and Thursdays 8:30-10:00. All lectures in lecture hall AS1.
Readings / Videos
For each lecture starting from the second one, there will be reading materials that the students should study before attending the lecture.
Introduction, Wed 21.9., no readings
Grasping, Thu 22.9. MLS, Chapter 5, Sections 1-4.2 on grasping
Discrete planning, Wed 28.9., LaValle, Sections 2.1-2.2.2, 2.3-2.3.2
Markov decision processes, Thu 29.9., S&B, chapters 2-2.3, 2.5-2.6, 3-3.8
Reinforcement learning, Wed 5.10., S&B, chapters 5-5.4, 5.6, 6-6.5
Policy gradient, Wed 19.10., Jan Peters, Policy gradient methods, http://www.scholarpedia.org/article/Policy_gradient_methods
Large POMDPs, Wed 26.10., Joni Pajarinen&Ville Kyrki, Robotic manipulation of multiple objects as POMDP, http://dx.doi.org/10.1016/j.artint.2015.04.001, Section 3.3, David Silver & Joel Veness, Monte Carlo planning in large POMDPs, www0.cs.ucl.ac.uk/staff/d.silver/web/Publications_files/pomcp.pdf
Optimal control and LQR, Wed 2.11.
Inverse reinforcement and apprenticeship learning, Thu 3.11., Pieter Abbeel, Machine Learning for Robotics, http://videolectures.net/ecmlpkdd2012_abbeel_learning_robotics/
Modeling skills, Wed 9.11., Jan Peters, A Road Map for Motor Skill Learning, http://videolectures.net/ecmlpkdd09_peters_rmmsl/