akolishchak

doom-net-pytorch

Reinforcement learning models in ViZDoom environment

hard-attention

Leaning hard attention model by policy gradient with rewards based on active inference.

geswall

GeSWall, Intrusion Prevention System

doom-net

Reinforcement learning models in ViZDoom environment

policy-autoencoder

Policy auto-encoder model that learns approximation of state transition and policy functions

ViZDoom

Doom-based AI Research Platform for Reinforcement Learning from Raw Visual Information. :godmode:

CarND-Behavioral-Cloning-P3

Starting files for the Udacity CarND Behavioral Cloning Project

CarND-Capstone

CarND-Extended-Kalman-Filter-Project

Self-Driving Car Nanodegree Program Starter Code for the Extended Kalman Filter Project

CarND-Kidnapped-Vehicle-Project

CarND-MPC-Project

CarND Term 2 Model Predictive Control (MPC) Project

CarND-Path-Planning-Project

Create a path planner that is able to navigate a car safely around a virtual highway

CarND-PID-Control-Project

CarND-Semantic-Segmentation

CarND-Traffic-Sign-Classifier-Project

Classify Traffic Signs.

CarND-Unscented-Kalman-Filter-Project

Self-Driving Car Nanodegree Program Starter Code for the Unscented Kalman Filter Project

defence

kmeans-kernels

Convolutional kernels learned by k-means

old_games

tch-rs

Rust bindings for the C++ api of PyTorch.

vae

Variational auto-encoder