How to turn non convex optimization problems to convex optimization problems and why - https://drive.google.com/file/d/1B2OJwvkmpR-l0M9odMq0qbSgoOuQhchw/view?usp=sharing

In this week meeting we'll cover an elementary example of sequential reasoning from section 4.2 in http://www.med.mcgill.ca/epidemiology/hanley/bios601/GaussianModel/JaynesProbabilityTheory.pdf

MC/TD strategies in re-enforcement learning - https://www.youtube.com/watch?v=WnVI11Mkf8w (video)

A good reinforcement resource -

https://urldefense.proofpoint.com/v2/url?u=https-3A__web.stanford.edu_class_psych209_Readings_SuttonBartoIPRLBook2ndEd.pdf&d=DwICAg&c=jf_iaSHvJObTbx-siA1ZOg&r=y_b69HJLyjn8lFwzYVfyxol578OEO4exeFDpgGN6MoQ&m=DP4VAIUt9yAI5EgscfOsnowTXUt4aKes1rBKt9ZmEi8&s=TS7tm5uW4x_prNkeiXMr6vWH-MGIATcvOwyA9A5QMRE&e=

Back to reinforcement learning and discuss the difference between MC and TD - https://drive.google.com/file/d/1QDjeHLUEk0kL6fyxTE_DGANDcyLK5zF0/view?usp=sharing

There is a deep relation between re-enforcement learning and recurring games which we'll start exploring next - https://drive.google.com/file/d/10FF4i_uURnzfqt6XnjK2CDWRgtoWxw3s/view?usp=sharing

We'll continue with reinforcement learning https://drive.google.com/file/d/1xOytbzidb-oBRpRUqsfMmALQXpVkTcOs/view?usp=sharing and discuss how to learn the value of one policy by simulating another.