e2crawfo

auto_yolo

Original implementation of Spatially Invariant Attend, Infer, Repeat (SPAIR) in TensorFlow.

hrr-scaling

Python/CUDA code to create a spiking neural network that can encode and traverse the Wordnet lexical database.

silot

Original tensorflow implementation of SILOT (Spatially Invariant, Label-free Object Tracking).

agricola

Work-in-progress implementation of agricola board game (revised edition) for training AI.

dps

Library for running and managing machine learning experiments with tensorflow and pytorch.

atari_rollouts

Rollouts gathered through training a PPO agent on Atari, originally used for evaluating unsupervised object detection/tracking networks SPAIR and SILOT.

backgrounds

clify

Wraps your python functions in a simple, mildly intelligent command line interface.

e2crawfo.github.io

gvgai_gym

gym

A toolkit for developing and comparing reinforcement learning algorithms.

gym-recording

Add-on package to gym, to record sequences of actions, observations, and rewards

hmmlearn

Hidden Markov Models in Python, with scikit-learn like API

mnist_arithmetic

monodepth2

Monocular depth estimation from a single image

notetaker

procgen

Procgen Benchmark: Procedurally Generated Game-Like Gym Environments

py-motmetrics

:bar_chart: Benchmark multiple object trackers (MOT) in Python

PyDSRL

Faithful Python implementation of the paper "Towards Deep Symbolic Reinforcement Learning" by Garnelo et al.

render_sprites

A custom tensorflow op which differentiably renders sprites to a canvas.

reverse_curric

rllab-curriculum

seq_lda

simple_set_dataset

Script for generating a dataset based on a simplified version of the game of SET ( https://en.wikipedia.org/wiki/Set_(card_game)).

spectral_dagger

sqair

Implementation of Sequential Attend, Infer, Repeat (SQAIR)

tensorflow

Computation using data flow graphs for scalable machine learning

tensorflow-reinforce

Implementations of Reinforcement Learning Models in Tensorflow

tracking-by-animation

train-procgen

Code for the paper "Leveraging Procedural Generation to Benchmark Reinforcement Learning"