ondrejbiza

bandits

Comparison of bandit algorithms from the Reinforcement Learning bible.

racetrack

An environment for tabular Reinforcement Learning agents.

tf_calibrate

Calibration of neural networks in Tensorflow.

bi-att-flow

Bidirectional Attention Flow

machine_intelligence_course

Tensorflow tutorials.

deep_learning_course

Deep Learning course at the Czech Technical University in Prague.

mcmc

Markov Chain Monte Carlo methods.

mdp_abstraction

Algorithms for minimization of Markov Decision Processes.

model_transfer

Replication of Transfer with Model Features in Reinforcement Learning -- Lehnert et al., 2018.

tfset

Interactive Tensorflow training.

bottleneck

Information bottleneck method.

caffe-tensorflow

Caffe models in TensorFlow

drl_gym

Deep Reinforcement Learning gym.

flownet2-tf

generic_text_DEICTIC

keras-yolo3

A Keras implementation of YOLOv3 (Tensorflow backend)

neural_abstraction

nnn

Numpy Neural Nets - a simple Deep Learning framework built on top of numpy.

python-torchfile

Deserialize torch-serialized objects from Python

ResidualAttentionNetwork-pytorch

a pytorch code about Residual Attention Network. This code is based on two projects from

symbolic_models

Examples of symbolic models defined in PDDL.

tensorflow-vgg

VGG19 and VGG16 on Tensorflow

tf-vqvae

Tensorflow Implementation of the paper [Neural Discrete Representation Learning](https://arxiv.org/abs/1711.00937) (VQ-VAE).

trepan

uncertain-mnist

Replication of Yarin Gal's Bayesian Deep Learning paper on MNIST.

VaST

An implementation of Variational State Tabulation, from the paper here: https://arxiv.org/abs/1802.04325.

vrep_homomorphisms