hartikainen
Previously: PhD student, intern @ Google/DeepMind, @rail-berkeley
Google / DeepMindHelsinki, Finland
Pinned Repositories
.doom.d
.dotfiles
My dotfiles
easy21
Reinforcement learning agents and environment for Easy21, a modified version of Blackjack
glow-flow
Modular tensorflow implementation for OpenAI's Glow.
rl-graph-signal-recovery
An attempt to apply reinforcement learning to graph signal recovery problem
simple-compiler
Simple compiler front-end created with Coco/R Compiler Generator
stanford-cs224n
Stanford CS224n: Natural Language Processing with Deep Learning
stanford-cs231n
Stanford CS231n: Convolutional Neural Networks for Visual Recognition
softlearning
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains. Includes the official implementation of the Soft Actor-Critic algorithm.
ray
Ray is an AI compute engine. Ray consists of a core distributed runtime and a set of AI Libraries for accelerating ML workloads.
hartikainen's Repositories
hartikainen/glow-flow
Modular tensorflow implementation for OpenAI's Glow.
hartikainen/.dotfiles
My dotfiles
hartikainen/hartikainen
hartikainen/mocap-environments
hartikainen/.doom.d
hartikainen/motion-diffusion-model
The official PyTorch implementation of the paper "Human Motion Diffusion Model"
hartikainen/mujoco_mpc
Model-Predictive Control for realtime synthesis of agile motor control using MuJoCo.
hartikainen/probability
Probabilistic reasoning and statistical analysis in TensorFlow
hartikainen/acme
A library of reinforcement learning components and agents
hartikainen/awesome-normalizing-flows
A list of awesome resources on normalizing flows.
hartikainen/bullet3
Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.
hartikainen/clipetty
Manipulate the system (clip)board with (e)macs from a (tty)
hartikainen/DeepMimic
Motion imitation with deep reinforcement learning.
hartikainen/dm_control
The DM Control Suite and Package is a tool for developing and testing reinforcement learning agents for the MuJoCo physics engine.
hartikainen/dustinlyons-nixos-config
Nix configuration for macOS / NixOS with starter templates, step-by-step guides, and more ✨
hartikainen/gitignore
A collection of useful .gitignore templates
hartikainen/gym
A toolkit for developing and comparing reinforcement learning algorithms.
hartikainen/hartikainen.github.io
hartikainen/jax
Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more
hartikainen/launchpad
hartikainen/mjx-bazel-test
hartikainen/mujoco
Multi-Joint dynamics with Contact. A general purpose physics simulator.
hartikainen/obj2mjcf
A CLI for processing composite Wavefront OBJ files for use in MuJoCo.
hartikainen/onshape-robotics-toolkit
A python library to facilitate interaction with Onshape's REST API
hartikainen/onshape-to-robot
Converting OnShape assembly to robot definition (SDF or URDF) through OnShape API
hartikainen/orbax
Orbax provides common checkpointing and persistence utilities for JAX users
hartikainen/ray
A high-performance distributed execution engine
hartikainen/softlearning
Softlearning is a reinforcement learning framework for training maximum entropy policies in continuous domains.
hartikainen/tensorflow
Computation using data flow graphs for scalable machine learning
hartikainen/trfl
TensorFlow Reinforcement Learning