till2
I enjoy building tools and learning new things. Passionate about Reinforcement Learning and Deep Learning.
Hasso-Plattner-InstitutePotsdam, Germany
Pinned Repositories
Gymnasium
An API standard for single-agent reinforcement learning environments, with popular reference environments and related utilities (formerly Gym)
brain_tumor_segmentation
Using different 2d and 3d U-Nets to segment MR brain scans.
ds4w-user-identification
User Identification from Accelerometer and Gyroscop Phone Sensors.
GPT_from_scratch
Building and training a Transformer on the Lex Fridman Podcast to answer questions.
hackatum
minimal-deeprl
Minimal implementations for algorithms defined in "Foundations of Deep Reinforcement Learning"
particle_sim
Agent based Covid-19 particle simulation using a SEIR-model.
policy-gradient-methods
Training agents in OpenAI-Gym with Policy-Gradient methods.
self-driving-car
Learning to drive a racing car with reinforcement learning in a learned world model.
till2.github.io
Personal notebook, blogposts and summaries.
till2's Repositories
till2/GPT_from_scratch
Building and training a Transformer on the Lex Fridman Podcast to answer questions.
till2/particle_sim
Agent based Covid-19 particle simulation using a SEIR-model.
till2/self-driving-car
Learning to drive a racing car with reinforcement learning in a learned world model.
till2/ds4w-user-identification
User Identification from Accelerometer and Gyroscop Phone Sensors.
till2/till2.github.io
Personal notebook, blogposts and summaries.
till2/hackatum
till2/pytorch_rl
A set of examples around pytorch in Vision, Text, Reinforcement Learning, etc.
till2/the-maze-runners
MAPF project with asp and pruning.
till2/Backpropagation-from-Scratch
Backpropagation for a toy MLP with one hidden layer.
till2/brain_tumor_segmentation
Using different 2d and 3d U-Nets to segment MR brain scans.
till2/policy-gradient-methods
Training agents in OpenAI-Gym with Policy-Gradient methods.
till2/3d-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.
till2/Blackjack-Tutorial
till2/Browsernet
till2/Chess-Challenge
https://youtu.be/iScy18pVR58
till2/CS50-AI-Projects
till2/DeepRule
till2/EvaP
a university course evaluation system written in Python using Django
till2/GridworldEnv
An educational environment for learning RL.
till2/gym-donkeycar
OpenAI gym environment for donkeycar simulator
till2/Gymnasium
A standard API for reinforcement learning and a diverse set of reference environments (formerly Gym)
till2/manim
A community-maintained Python framework for creating mathematical animations.
till2/RL-Bandit
till2/Search-Algos-Visual
Visualization of popular graph search algorithms.
till2/SEwithML
Projects on Software Engineering with Machine Learning
till2/TFJS-BrowserNet
till2/Thaiane
till2/till2
till2/vectorized-envs-tutorial
Gymnasium tutorial for vectorized environments (using A2C with GAE).
till2/Youtube-Code-Repository
Repository for most of the code from my YouTube channel