Wraps the environment with timing perturbations. The agent runs normally — no internal intervention. Deployment scenarios (jitter, delay, spike) model realistic conditions. Stress scenarios (5x speed) test extreme resilience.
| Category | Scenario | Return (% nominal) | 95% CI | RMSE ratio | Return Change |
|---|---|---|---|---|---|
| Deployment | Speed jitter (2 +/- 1) | 66% | 52%–83% *** | 1.61x | +33.9% |
| Deployment | Observation delay (1 step) | 82% | 72%–94% *** | 0.97x | +17.8% |
| Deployment | Mid-episode spike (1-5-1) | 23% | 18%–30% *** | 1.32x | +77.1% |
| Stress | 5x Speed (unseen frequency) | 12% | 9%–16% *** | 1.78x | +87.7% |
Agent degrades under deployment timing conditions. Recommended fix: train with speed randomization (jitter/delay/spike augmentation).