Docs/Build/Regulation & tracking
CLIENT 0.4.3PYTHON 3.8+

Regulation & tracking

Hold a measured output at a target while the system drifts.

Regulation is the clearest operating regime: parallel readout, writable controls, a locally monotone response, and a target that moves more slowly than the loop can track.

Channel handling is automatic across supported locally monotone plants. The customer loop keeps the same compact measurement contract from start to finish.

Use related-task warm starts when targets arrive as a stream. Start the next job from the last accepted configuration.

PYTHON
opt = SWCOptimizer(key, n=len(x0), mode="regulation", target=target)
x = opt.start(x0)
for _ in range(rounds):
    x = opt.step(measure(x), target=target)
opt.end()
Need the answer on your plant?

Run the envelope, then race the runtime and your incumbent under the same measured budget.

Start evaluation