List your company
ResearchFormerly WizWand

Reward Estimation on Standard bus engine replacement simulation without dummy variables

0.12MAPEGLADIUS
-4.642427.503859.6591.7962Feb 19, 2025
Updated 6mo ago

Evaluation results

MethodLinks
GLADIUSMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=50002025.020.120.06
GLADIUSMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=25002025.020.130.06
RustMethod Category=Oracle Baselines, No. of Trajectories (H=100)=50002025.020.40.06
ML-IRLMethod Category=Oracle Baselines, No. of Trajectories (H=100)=50002025.020.430.26
GLADIUSMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=10002025.020.520.22
GLADIUSMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=5002025.020.550.2
ML-IRLMethod Category=Oracle Baselines, No. of Trajectories (H=100)=25002025.020.620.35
ML-IRLMethod Category=Oracle Baselines, No. of Trajectories (H=100)=10002025.020.640.48
RustMethod Category=Oracle Baselines, No. of Trajectories (H=100)=25002025.020.680.22
RustMethod Category=Oracle Baselines, No. of Trajectories (H=100)=10002025.020.710.49
ML-IRLMethod Category=Oracle Baselines, No. of Trajectories (H=100)=5002025.020.840.59
GLADIUSMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=2502025.020.840.51
RustMethod Category=Oracle Baselines, No. of Trajectories (H=100)=5002025.020.90.56
ML-IRLMethod Category=Oracle Baselines, No. of Trajectories (H=100)=2502025.021.10.78
RustMethod Category=Oracle Baselines, No. of Trajectories (H=100)=2502025.021.370.77
SAmQMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=10002025.021.550.46
SAmQMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=5002025.023.130.86
GLADIUSMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=502025.023.441.28
RustMethod Category=Oracle Baselines, No. of Trajectories (H=100)=502025.023.621.7
ML-IRLMethod Category=Oracle Baselines, No. of Trajectories (H=100)=502025.023.621.74
SAmQMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=2502025.023.651
SAmQMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=502025.024.921.2
BCMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=50002025.0246.458.22
BCMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=25002025.0262.6110.75
BCMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=5002025.0271.9212.44
BCMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=2502025.0272.0413.21
BCMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=10002025.0272.1712.11
BCMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=502025.0280.5512.82
IQ-learnMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=25002025.02111.7723.99
IQ-learnMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=2502025.02112.8627.31
IQ-learnMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=10002025.02112.9824.12
IQ-learnMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=5002025.02113.2725.54
IQ-learnMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=502025.02114.1326.6
IQ-learnMethod Category=Neural Network, No Knowledge of Transition Probabilities, No. of Trajectories (H=100)=50002025.02119.1822.55