Repositórios
Repositórios de Kaixhin
Actor-critic with experience replay
Persistent advantage learning dueling double DQN for the Arcade Learning Environment
Torch implementations of various types of autoencoders
Distributed A3C
Episodic Control
Reinforcement Learning Assignment: Easy21
Fully convolutional networks for semantic segmentation
Future Gadget Laboratory
Future Gadget Machine
Generalised UDRL
Team Inforaptor's project for IC Hack '14
Incremental Slow Feature Analysis
Minimal Criterion Artist Collective
Noisy Networks for Exploration
Deep Planning Network: Control from pixels by latent planning with learned dynamics
Rainbow: Combining Improvements in Deep Reinforcement Learning
ML models trained on the SARCOS dataset
Course Info for VIP-GEAI