An interactive research platform demonstrating offline reinforcement learning for taxi zone dispatching. Explore forecasts, compare policies, and simulate AI-driven decisions using real NYC TLC data.
Interactive map of Manhattan taxi zones with demand levels. Click a zone to view details and run simulations.
Configure inputs and run the AI pipeline to simulate a taxi dispatching decision. All results are simulation-based.
Comparison of all evaluated policies across reward, revenue, and utilization metrics.
Select a zone on the map to see its 24-hour demand forecast compared with historical averages.
Key performance metrics from the v2.0 research release. All values from calibrated simulation evaluation.
Note: All metrics are from calibrated simulation evaluation. Not real deployment data.
Explore the full research documentation, reproduction guide, and model cards.