Post date: Apr 17, 2017 8:2:49 AM
Lecture: Value function approximation
Reading: Slides by David Silver, Sutton and Barto Chapter 9-11 (skipping TD(λ))
Lab: TBA
Project: (due Apr 20) Implement and train all your models to replicate the results of your paper. You can consult the professor if there are multiple results and you think you can only replicate a subset. Update your research docs (doc,sheet,slides,latex,github) to reflect your results.
Project related assignments will only be graded when they are 100% complete. Late completion will be graded based on the following formula: (1/2)+(1/2)^(d/3+1) where d is the number of days late.