IoV Defense Strategy on IoV security environment 80 episodes (test)
0ASRPPO w/ Quantum Belief
Evaluation Results
| Method | Links | |||||
|---|---|---|---|---|---|---|
| PPO w/ Quantum BeliefBelief Model=Quantum Amplitude, Algorithm=PPO (neural network)2026.06 | 0 | 27.495 | 1.907 | 3.636 | 100 | |
| Q-Learning w/ Classical BeliefBelief Model=Classical Bayesian, Algorithm=Q-Learning (tabular)2026.06 | 4.1 | 40.621 | 4.27 | 18.236 | 81.2 | |
| Random PolicyBelief Model=None, Algorithm=Random action2026.06 | 23.9 | 58.665 | — | 25.609 | 73.9 | |
| PPO w/ Classical BeliefBelief Model=Classical Bayesian, Algorithm=PPO (neural network)2026.06 | 24.7 | 69.348 | 6.087 | 37.054 | 68.3 | |
| Guo et al.Belief Model=Classical Bayesian, Algorithm=Q-Learning + WoLF-PHC2026.06 | 50 | — | — | — | — | |
| No MitigationBelief Model=None, Algorithm=Static (monitor only)2026.06 | — | 99.635 | — | — | — |