PeeteKeesel

basic-rl-algorithms

:robot: Implementation and short explanation of basic RL algorithms, reproducing the simulations from Andrej Kaparthy's REINFORCEjs library.

gnn-for-drug-response-prediction

:dna: Process repository for my master thesis attacking drug response prediction on cancer cell-lines using bi-modal graph neural networks

sokoban-ai

:evergreen_tree: Teaching an AI to solve Sokoban using AlphaGo-Zero style RL & Single-Player MCTS.

bayes-opt-battle

:bar_chart: Comparison of Bayesian hyperparameter optimization libraries in python

coursera-summaries

:mag: Labs, quizzes, answers and explanations for Coursera specialisations and courses

reinforce-py

🐍 Implementation of the REINFORCEjs library from Kaparthy in Python

CookingRecipes

:avocado: List of awesome food recipes.

PaperGPT

:microscope: Choose a academic research papers and get a TL;DR for it in seconds.

ai-summer-schools

:classical_building: Curated list of artificial-intelligence related summer schools.

lazypredict

Lazy Predict help build a lot of basic models without much code and helps understand which models works better without any parameter tuning

PeeteKeesel