Site Search  

Teaching » Syllabus: Current Topics in Statistical Learning - Robot Learning

All downloadable documents are Adobe Acrobat PDF documents. You can obtain Acrobat for free by following the link from the Adobe Icon.

Note: This syllabus will be modified continuously to accommodate the progress and interests of the course participants!

DateTopicAssignments
Aug. 24Introductionsend email to sschaal@usc.edu with two lines:
# First_Name Last_Name
your_email@mailer.com
Aug. 31Efficient learning with linear models: Locally Weighted Learning (LWL)Incremental LWL,
LWL for Control,
Slides
Sept. 7Locally Weighted Learning (LWL) and Dimensionality ReductionDimensionality Reduction, Slides
Sept. 14Reinforcement Learning with Policy GradientsReinforcement Learning,
Policy Gradients, Slides
Sept. 21Robot Learning Talk by Martin Riedmiller,
Finish Policy Gradients,
Reinforcement Learning,
Policy Gradients, Slides
Sept. 28Bayesian Learning with EM and Variational Approximations,
Gaussian Processes
Introduction, ConvexDuality, MacKay Ch.33, Gaussian Processes
Oct. 5Learning/Imitation with Motor PrimitivesLearning Motor Primitives,
Learning Attractor Landscapes as Movement Primitives,
see also Imitation Learning and Motor Primitives
Oct. 12Project SuggestionsPPT Slides
Oct. 19Project DiscussionGroups introduce their projects, goals, approaches
Oct. 26Project Progress, Discussions,
Maximum Margin Planning
Groups present their project progress,
Paper 1,Paper 2
Nov. 2Personal meetings with groups 
Nov. 9Groups present their project progress,
Finish Maximum Margin Planning discussion,
Product of Experts


Paper 1
Nov. 16Product of Experts,
Remarks on on-line learning,
Personal meetings with groups on demand.
 
Nov. 30Final Project presentations of all groups. 
Designed by: Nerses Ohanyan & Jan Peters
Page last modified on January 13, 2012, at 02:41 AM