Lyft has built a platform for developing, training, and serving Reinforcement Learning models for decision making problems. They focus on Contextual Bandits and highlight the benefits of RL models for optimizing the decision making process in changing environments.

5m read time From eng.lyft.com
Post cover image
Table of contents
ArchitectureLibraryVowpal WabbitLyft RL LibraryCoreLibraryEvaluationServingTrainingWarm StartContinuous Updates

Sort: