Test Generation on CAV-Gym n=5 (test)
40.2Accuracy (%)Q-Learning
Evaluation Results
| Method | Links | |||
|---|---|---|---|---|
| Q-LearningDescription=Use RL to make optimal decisions2025.12 | 40.2 | -4.5633 | 13.2895 | |
| ProximityDescription=Select an action according to a threshold distance2025.12 | 38.6 | -8.2536 | 10.412 | |
| MPCDescription=Predict system behaviour and optimise a control sequence to minimise a cost2025.12 | 37 | -3.7102 | 24.57 | |
| ElectionDescription=As a proximity agent with proximity-trigger conditions2025.12 | 34 | -6.2533 | 10.9014 | |
| Constrained randomDescription=Select a random action within a restricted action space2025.12 | 29.8 | -26.719 | 7.9186 | |
| RandomDescription=Select a random action from the action space2025.12 | 22.8 | -20.6095 | 8.1546 |