hardmaru

estool. Evolution Strategies Tool

sketch-rnn. Multilayer LSTM and Mixture Density Network for modelling path-level SVG Vector Graphics data in TensorFlow

slimevolleygym. A simple OpenAI Gym environment for single and multi-agent reinforcement learning

WorldModelsExperiments. World Models Experiments

write-rnn-tensorflow. Generative Handwriting using LSTM Mixture Density Network with TensorFlow

pytorch_notebooks. tutorial notebooks

cppn-gan-vae-tensorflow. Train CPPNs as a Generative Model, using Generative Adversarial Networks and Variational Autoencoder techniques to produce high resolution images.

cppn-tensorflow. Very Simple and Basic Implementation of Compositional Pattern Producing Network in TensorFlow

sketch-rnn-datasets. optional extra vector image datasets for sketch-rnn

neuralslimevolley. Neural Slime Volleyball

supercell. supercell

rnn-tutorial. RNN Tutorial for Artists

backprop-neat-js. Neural Network Evolution Playground with Backprop NEAT

resnet-cppn-gan-tensorflow. Using Residual Generative Adversarial Networks and Variational Auto-encoder techniques to produce high resolution images.

astool. Augmented environments with RL

image-notebook. image-notebook

neurogram. neurogram

gecco-tutorial-2019. 2019 talk at GECCO

mdn_jax_tutorial. Mixture Density Networks (Bishop, 1994) tutorial in JAX

netart-js. quick hacked together js demo to implement fixed-topology cppn in the web browser for interactive usage

presentations. presentations

cppn-gan-vae-cifar-tensorflow. First attempt to use the previous CPPN-GAN-VAE model to train on CIFAR-10 images.

sketch-rnn-flowchart. trained sketch-rnn / deployed with sketch-rnn-js on flowchart dataset

convnetjs. Deep Learning in Javascript. Train Convolutional Neural Networks (or ordinary ones) in your browser.

kanji2kanji. Reproduce domain transfer results in Deep Learning for Classical Japanese Literature

paperjs_box2d. demo of working with box2d and paper.js

RainbowSlimeVolley. Using Rainbow implementation in Chainer RL for Slime Volleyball Pixel Environment

sketch-rnn-poster. Poster for "A Neural Representation for Sketch Drawings" for ICLR 2018 Conference

rlzoo. fork of rl-baseline-zoo

magenta-js. Magenta.js: Music and Art Generation with Machine Intelligence in the Browser

quickdraw-ndjson-to-npz. Convert RAW Quickdraw datafiles into stroke-based .npz format with RDP at variable epsilon for sketch-rnn

cantonese-list. List of 4000 Chinese characters sorted by historical usage frequency, with Cantonese yale romanization and definition

sema-demo. sketch-rnn demo for seoul mediacity biennale 2018

diff-vae-tensorflow. skeleton variation encoder code in tensorflow

cma. Fork of cma-es library by Nikolaus Hansen

pybullet_animations. pybullet_animations

magenta-demos. Demonstrations of Magenta Models

Dynamic_Neural_Manifold. Jupyter Notebook

creatures. autonomous creatures written in processing / processing.js

PyTorch-NEAT. Python

DeepPrivacy. DeepPrivacy: A Generative Adversarial Network for Face Anonymization

tensorflow_with_latest_papers. Implementation of Newest RNN and Seq2Seq Features

fast-weights. Implementation of the paper [Using Fast Weights to Attend to the Recent Past](https://arxiv.org/abs/1610.06258)

trpo. Trust Region Policy Optimization with TensorFlow and OpenAI Gym

gym. A toolkit for developing and comparing reinforcement learning algorithms.

zombie. A* search algorithm example, zombie chasing humans

WorldModels. World Models with TensorFlow 2

NeurIPS19-SBDRL. Code for NeurIPS 2019 paper: "Symmetry-Based Disentangled Representation Learning requires Interaction with Environments" by H. Caselles-Dupré, M. Garcia-Ortiz and D. Filliat.

worldmodels.github.io. World Models

tshirtai.

recurrentjs. Deep Recurrent Neural Networks and LSTMs in Javascript. More generally also arbitrary expression graphs with automatic differentiation.

char-rnn-tensorflow. Multi-layer Recurrent Neural Networks (LSTM, RNN) for character-level language models in Python using Tensorflow

chainerrl. ChainerRL is a deep reinforcement learning library built on top of Chainer.

bnlstm. Batch normalized LSTM for tensorflow

bullet3. Bullet Physics SDK: real-time collision detection and multi-physics simulation for VR, games, visual effects, robotics, machine learning etc.