Name: Kristian Hartikainen
Type: User
Company: Google / DeepMind
Bio: PhD student at WhiRL at Oxford. Research intern at Google/DeepMind.
Previously at the Robotic AI and Learning Lab (RAIL) at UC Berkeley.
Twitter: kristianhartika
Location: London, United Kingdom
Blog: https://hartikainen.github.io/
Kristian Hartikainen's Projects
My dotfiles
My Emacs config stuff
A library of reinforcement learning components and agents
Useful extra functionality for TensorFlow 2.0 maintained by SIG-addons
Airflow is a system to programmatically author, schedule and monitor data pipelines.
A list of awesome resources on normalizing flows.
Berkeley CS 294: Deep Reinforcement Learning
Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
Manipulate the system (clip)board with (e)macs from a (tty)
Motion imitation with deep reinforcement learning.
The DM Control Suite and Package is a tool for developing and testing reinforcement learning agents for the MuJoCo physics engine.
Code for "Divide-and-Conquer Reinforcement Learning"
Dopamine is a research framework for fast prototyping of reinforcement learning algorithms.
T-106.5300 Embedded Systems Car project
Nix configuration for macOS / NixOS with starter templates, step-by-step guides, and more ✨
Reinforcement learning agents and environment for Easy21, a modified version of Blackjack
Project Euler stuff
Feature Store for Machine Learning
Formulagame built for a Aalto University's programming course
A collection of useful .gitignore templates
Modular tensorflow implementation for OpenAI's Glow.
A toolkit for developing and comparing reinforcement learning algorithms.
Hacked, together with couple of Jiiri founders, a small shopping-list application to scratch our own itch.
jiiri