A Better Match for Drivers and Riders: Reinforcement Learning at Lyft.
Xabi AzagirreAkshay BalwallyGuillaume CandeliNicholas ChamandyBenjamin HanAlona KingHyungjun LeeMartin LoncaricSébastien MartinVijay NarasimanZhiwei (Tony) QinBaptiste RichardSara SmootSean TaylorGarrett J. van RyzinDi WuFei YuAlex ZamoshchinPublished in: INFORMS J. Appl. Anal. (2024)
Keyphrases
- reinforcement learning
- function approximation
- optimal policy
- learning algorithm
- reinforcement learning algorithms
- model free
- machine learning
- robotic control
- temporal difference learning
- key factors
- markov decision processes
- multi agent
- dynamic programming
- learning process
- multi agent reinforcement learning
- state space
- active learning
- optimal control
- partially observable
- decision trees
- markov decision process
- decision making
- reinforcement learning methods
- autonomous learning
- policy search
- database
- direct policy search