GitHub - zyxue/sutton-barto-rl-exercises at a845977f31d166e8987a7848b64807aae7f3ca4e

This repo originall intended to host only my answers to the exercies for the book by Sutton & Barton, Reinforcement Learning: An Introduction

A free pdf can be found here

But now examples of common supervised/unsupervised learning models will also be put here, in the supervised & unsupervised directories

Pull requests and bug report are welcome.

Note: if you find the formatting some notebooks (esp. with many equations) doesn't look good on github,, try visualize them on http://nbviewer.jupyter.org/github/zyxue/sutton-barto-rl-exercises/tree/master/.

Name		Name	Last commit message	Last commit date
Latest commit Cannot retrieve latest commit at this time. History 179 Commits
linear_algebra		linear_algebra
miscellaneous		miscellaneous
plotting_notes		plotting_notes
reinforcement		reinforcement
shap		shap
stats		stats
supervised		supervised
unsupervised		unsupervised
.gitignore		.gitignore
README.md		README.md
about-NaN.ipynb		about-NaN.ipynb
eda_imports.py		eda_imports.py
information-entropy-3D-TODO.ipynb		information-entropy-3D-TODO.ipynb
jacarrd-similarity-vs-simon-similarity.ipynb		jacarrd-similarity-vs-simon-similarity.ipynb
numba-cosine-distance-benchmark.ipynb		numba-cosine-distance-benchmark.ipynb
t-digest-experiment.ipynb		t-digest-experiment.ipynb

Provide feedback