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