Nat-D

GMVAE

Deep Unsupervised Clustering with Gaussian Mixture Variational Autoencoders

FeatureControlHRL

Feature Control as Intrinsic Motivation for Hierarchical Reinforcement Learning

SVAE-Torch

teaching

code for teaching deep learning

Autoencoders

Torch implementations of various types of autoencoders

baselines

OpenAI Baselines: high-quality implementations of reinforcement learning algorithms

cooking_zoo

CookingZoo: a gym-cooking derivative to simulate a complex cooking environment

DQN-Tensorflow

DQN implementation with Tensorflow + gym

gym-cooking

gym-cooking: Code for "Too many cooks: Bayesian inference for coordinating multi-agent collaboration", Winner of the CogSci 2020 Computational Modeling Prize in High Cognition, and a NeurIPS 2020 CoopAI Workshop Best Paper.

gym-maze

A basic 2D maze environment where an agent start from the top left corner and try to find its way to the bottom left corner.

split-vae

Original implementation of Separated Paths for Local and Global Information framework (SPLIT) in TensorFlow 2.

nat-d.github.io

RoboND-Python-StarterKit

Repository to setup your Python environment for RoboND

sebas

universe-starter-agent

A starter agent that can solve a number of universe environments.

Variational-Ladder-Autoencoder

Implementation of VLAE

varuna-hackathon