top of page

semarx

Drift detection for RL and control agents

Reads observations and actions from the interaction stream and flags when an agent loses its grip on the environment, often while reward still looks normal. No policy weights, no reward access, no retraining.

chart6_rl_detection.png

Results

  1. Detection: 69% vs 44% for reward-based monitoring, at the same false-alarm budget (168 perturbation trials, 21 agents, MuJoCo HalfCheetah).

  2. Coverage: 50 degradations caught that the reward signal missed entirely; reward caught 8 the monitor missed.

  3. Perturbations: environment-side changes (gravity, external forces) and agent-side degradation (observation noise, action corruption).

  4. ​Readout: one reading per window from 17 observation and 6 action dimensions; no policy weights or reward signal.

Source: Am I Still Coupled to My Environment? Task-Agnostic Runtime Telemetry from the Reinforcement-Learning Interaction Loop. Hafez, Wei (2026). Preprint, Research Square.

bottom of page