Kaixhin

Rainbow: Combining Improvements in Deep Reinforcement Learning

The Hitchiker's Guide to PyTorch

Imitation learning algorithms

Compilation of Dockerfiles with automated builds enabled on the Docker Registry

Torch implementations of various types of autoencoders

Deep Planning Network: Control from pixels by latent planning with learned dynamics

Persistent advantage learning dueling double DQN for the Arcade Learning Environment

Actor-critic with experience replay

Future Gadget Laboratory

Basic versions of agents from Spinning Up in Deep RL written in PyTorch

Fully convolutional networks for semantic segmentation

Noisy Networks for Exploration

Weight initialisation schemes for Torch7 neural network modules

Reinforcement learning environments for Torch7

Future Gadget Machine

Malmo Collaborative AI Challenge - Team Pig Catcher