17 open source projects by Kaixhin

Future Gadget Laboratory

Actor-critic with experience replay

Fully convolutional networks for semantic segmentation

Noisy Networks for Exploration

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

Weight initialisation schemes for Torch7 neural network modules

Reinforcement learning environments for Torch7

Imitation learning algorithms

Rainbow: Combining Improvements in Deep Reinforcement Learning

Malmo Collaborative AI Challenge - Team Pig Catcher

Reinforcement Learning Assignment: Easy21

The Hitchiker's Guide to PyTorch

Torch implementations of various types of autoencoders

Persistent advantage learning dueling double DQN for the Arcade Learning Environment

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

Future Gadget Machine

Distributed A3C