Jonas Stepanik's repositories
Soft-Actor-Critic
Implementation of Soft Actor-Critic Reinforcement Learning Algorithm using Pytorch.
Streamlined-Off-Policy-Learning
This is an implementation of "Algorithm 2 SOP with Emphasizing Recent Experience" proposed in the paper "Striving for Simplicity and Performance in Off-Policy DRL: Output Normalization and Non-Uniform Sampling" by Che Wang, Yanqiu Wu, Quan Vuong and Keith Ross.
DDPG-tensorflow
Simple and easy to read implementation of the Reinforcement Learning algorithm DDPG.
Algorithms-in-C
This repo consists of some algorithms I coded in C. They are not supposed to be super efficient nor well implemented, I just coded them for learning purposes!
Wormhole-Visualization
This is a simple Python visualization of a Wormhole using numpy and matplotlib.
Image-compression-with-Stacked_Autoencoder
Using a Stacked Autoencoder with 3 hidden layers to compress MNIST images from 28x28 pixels to 14*14 pixels vice-versa. The deep neural network was built using the open-source python library Tensorflow.
MyVimrc
This repo holds my .vimrc file which is an edited version of @amix3k's vimrc (https://github.com/amix/vimrc).
ptan
PyTorch Agent Net: reinforcement learning toolkit for pytorch
pytorch-gpu-benchmark
Using the famous cnn model in Pytorch, we run benchmarks on various gpu.
simple-pid
A simple and easy to use PID controller in Python
tinygrad
You like pytorch? You like micrograd? You love tinygrad! ❤️