Share your thoughts, 1 month free Claude Pro on usSee more
WorkDL logo mark

Taxi

Benchmarks

Task NameDataset NameSOTA ResultTrend
Event PredictionTAXI
RMSEΔt0.236
40
Goal-oriented DialogueTaxi
Success Rate85.53
32
Vulnerable Agent IdentificationTaxi environment
Runtime (hours)0.5341
24
Event ForecastingTaxi
RMSE0.32
23
Event PredictionTAXI (test)
OTD8.324
22
Multi-horizon forecastingTaxi
Inter-event Time RMSE0.285
15
Taxi DomainTaxi Standard
Accuracy83.98
14
Probabilistic Forecastingtaxi
CRPS0.119
13
Conditional Coverage for Partially Revealed OutputsTaxi
ERT (%)2.09
11
Event count predictionTaxi (test)
MARE28
11
Unconditional generation of event sequencesTaxi (test)
MMD (1e-2)3.1
11
RegressionTaxi (test)
NLL3.112
11
RegressionTaxi
NLL3.112
11
Conformal PredictionTaxi
Volume0.003
11
Probabilistic forecastingtaxi (test)
MSE0.16
11
Time-series ForecastingTaxi
NRMSE Sum0.1516
10
Marked Temporal Point Process PredictionTaxi (test)
RMSE0.323
10
Point Process Intensity EstimationTaxi
Ltest Score7,246
10
Density estimationTaxi (test)
MMD0.04
10
Next-event predictionTaxi
Time RMSE0.298
9
Conformal PredictionTaxi (test)
Coverage91
8
Multi-output Conformal PredictionTaxi
ERT (%)7.95
8
Conformal PredictionTaxi
ERT0.4
8
Forecasting Temporal Point ProcessesTaxi (test)
Sequence distance (l2)1.8
8
Multivariate RegressionTaxi
Coverage98.9
8
Showing 25 of 45 rows