nsavinov

dm-haiku

JAX-based neural network library

jax

Composable transformations of Python+NumPy programs: differentiate, vectorize, JIT to GPU/TPU, and more

spriteworld

Spriteworld: a flexible, configurable python-based reinforcement learning environment

bsuite

bsuite is a collection of carefully-designed experiments that investigate core capabilities of a reinforcement learning (RL) agent

sleep-scoring

Code for automatic scoring of EEG recordings

episodic-curiosity

Tensorflow/Keras code and trained models for Episodic Curiosity Through Reachability

CAL

[CoRL'18] Conditional Affordance Learning

acs-mods

neural-path-matching

zeroshot-imitation

[ICLR 2018] TensorFlow code for zero-shot visual imitation by self-supervised exploration

ViZDoom

Reinforcement Learning environments based on the 1993 game Doom :godmode:

Open3D

Open3D: A Modern Library for 3D Data Processing

Learning-to-navigate-without-a-map

The goal of the project is to determine how well deep learning is suited for planning under incomplete information.

mc-cnn

Stereo Matching by Training a Convolutional Neural Network to Compare Image Patches

multipathnet

A Torch implementation of the object detection network from "A MultiPath Network for Object Detection" (https://arxiv.org/abs/1604.02135)

TI-pooling

TI-pooling: transformation-invariant pooling for feature learning in Convolutional Neural Networks