Fully Connected

Bringing ML practitioners together

Fully Connected is your home for curated tutorials, conversations with industry leaders, deep dives into the newest ML research, and a whole lot more.

FeaturedBlog PostsEventsGradient DissentForumComputer VisionNLPReinforcement LearningPyTorchKeras or TensorFlowfastaiHugging FaceScikitKaggleTwo Minute PapersReproducibility ChallengePaper OverviewVisualizationTutorialQuestionDiscussionResourcesShowcaseWebinarAMAPaper Reading GroupSalonfastbookCustom Charts
Training Reproducible Robots with W&B
Armand du Parc Locmaria
Dynamic Convolution: Attention over Convolution Kernels (CVPR 2020)
Sachin Malhotra
VIDEO: Teaching a Self-Driving RC Car To Obey the Law. And Then Break It.
Justin Tenuto
Webinar: RL experiments w/ Stable-Baselines3 and W&B
Andrea Pessl
Gym-μRTS: Toward Affordable Deep Reinforcement Learning Research in Real-Time Strategy Games
Costa Huang, Chris Bamford
Getting Started with Safelife
Stacey Svetlichnaya
Tuning Safety Penalties in Reinforcement Learning
Carroll Wainwright
Action Guidance: Getting the Best of Sparse Rewards and Shaped Rewards for Real-Time Strategy Games
Costa Huang
Measuring Safety in Reinforcement Learning
Stacey Svetlichnaya
Track and Tune Your Reinforcement Learning Models
Yash Kotadia
Learning Dexterity End-to-End
Alex Paino
Transformer Reinforcement Learning
Leandro von Werra
Adversarial Policies in Multi-Agent Settings
Stacey Svetlichnaya
Deep Q Networks with the Cartpole Environment
Jari