Yes, Google Maps uses inverse reinforcement learning[1] (IRL) to improve its routing feature. The "Massively Scalable Inverse Reinforcement Learning in Google Maps[1]" paper describes how they have used IRL to recover users' preferences and improve the global route match rate[1] in Google Maps by 16–24%. They have also introduced a new IRL algorithm called Receding Horizon Inverse Planning[1] (RHIP) to achieve more accurate and faster route suggestions.
Sign Up To Try Advanced Features
Get more accurate answers with Super Search, upload files, personalized discovery feed, save searches and contribute to the PandiPedia.
Sorry, Pandi could not find an answer.
Let's look at alternatives:
- Modify the query.
- Start a new thread.
- Remove sources (if manually added).
- Request a manual search from our human research team.