Till Zemann's repositories
ds4w-user-identification
User Identification from Accelerometer and Gyroscop Phone Sensors.
3d-shapes
This repository contains the 3D shapes dataset, used in Kim, Hyunjik and Mnih, Andriy. "Disentangling by Factorising." In Proceedings of the 35th International Conference on Machine Learning (ICML). 2018. to assess the disentanglement properties of unsupervised learning methods.
EvaP
a university course evaluation system written in Python using Django
till2.github.io
Personal notebook, blogposts and summaries.
Chess-Challenge
https://youtu.be/iScy18pVR58
gym-donkeycar
OpenAI gym environment for donkeycar simulator
self-driving-car
Learning to drive a racing car with reinforcement learning in a learned world model.
particle_sim
Agent based Covid-19 particle simulation using a SEIR-model.
Gymnasium
A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)
GPT_from_scratch
Building and training a Transformer on the Lex Fridman Podcast to answer questions.
Backpropagation-from-Scratch
Backpropagation for a toy MLP with one hidden layer.
the-maze-runners
MAPF project with asp and pruning.
vectorized-envs-tutorial
Gymnasium tutorial for vectorized environments (using A2C with GAE).
policy-gradient-methods
Training agents in OpenAI-Gym with Policy-Gradient methods.
brain_tumor_segmentation
Using different 2d and 3d U-Nets to segment MR brain scans.
GridworldEnv
An educational environment for learning RL.
Search-Algos-Visual
Visualization of popular graph search algorithms.
pytorch_rl
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
manim
A community-maintained Python framework for creating mathematical animations.
Youtube-Code-Repository
Repository for most of the code from my YouTube channel