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) | 25% | 24%–28% *** | 2.38x | +74.6% |
| Deployment | Observation delay (1 step) | 4% | 2%–5% *** | 3.79x | +96.2% |
| Deployment | Mid-episode spike (1-5-1) | 91% | 86%–98% *** | 1.07x | +9.1% |
| Stress | 5x Speed (unseen frequency) | -9% | -11%–-8% *** | 4.82x | +109.3% |
Agent degrades under deployment timing conditions. Recommended fix: train with speed randomization (jitter/delay/spike augmentation).