Your first Scipy optimization with Bluesky Adaptive#
In this tutorial, you will learn the three core concepts of Bluesky Adaptive: DOFs (the parameters you can adjust), objectives (what you want to optimize), and the Agent (which coordinates the optimization). We’ll optimize a simple mathematical function using simulated devices—the same patterns apply to real hardware.
Setup#
First, let’s import what we need and start the data infrastructure:
import logging
import time
from typing import Any
from bluesky.protocols import HasHints, HasParent, Hints, NamedMovable, Readable, Status
from bluesky.run_engine import RunEngine
from bluesky_tiled_plugins import TiledWriter
from tiled.client import from_uri
from tiled.client.container import Container
from tiled.server import SimpleTiledServer
from bluesky_adaptive.scipy import SCP, ScipyCFG, Objective, RangeDOF, Scipy
# Suppress noisy logs from httpx
logging.getLogger("httpx").setLevel(logging.WARNING)
# Start a local Tiled server for data storage
tiled_server = SimpleTiledServer()
# Set up the Bluesky RunEngine and connect it to Tiled
RE = RunEngine({})
tiled_client = from_uri(tiled_server.uri)
tiled_writer = TiledWriter(tiled_client)
RE.subscribe(tiled_writer)
0
Creating simulated devices#
Bluesky controls devices through protocols. For this tutorial, we create simple simulated “movable” devices. In real experiments, you would use Ophyd devices or similar—the code below is just boilerplate to simulate hardware:
class AlwaysSuccessfulStatus(Status):
def add_callback(self, callback) -> None:
callback(self)
def exception(self, timeout=0.0):
return None
@property
def done(self) -> bool:
return True
@property
def success(self) -> bool:
return True
class ReadableSignal(Readable, HasHints, HasParent):
def __init__(self, name: str) -> None:
self._name = name
self._value = 0.0
@property
def name(self) -> str:
return self._name
@property
def hints(self) -> Hints:
return {"fields": [self._name], "dimensions": [], "gridding": "rectilinear"}
@property
def parent(self) -> Any | None:
return None
def read(self):
return {self._name: {"value": self._value, "timestamp": time.time()}}
def describe(self):
return {self._name: {"source": self._name, "dtype": "number", "shape": []}}
class MovableSignal(ReadableSignal, NamedMovable):
def __init__(self, name: str, initial_value: float = 0.0) -> None:
super().__init__(name)
self._value: float = initial_value
def set(self, value: float) -> Status:
self._value = value
return AlwaysSuccessfulStatus()
Defining DOFs and objectives#
DOFs (degrees of freedom) are the parameters the optimizer can adjust. Objectives are what you want to optimize. Here we define two DOFs (x1 and x2) that can range from -5 to 5, and one objective (the Himmelblau function) that we want to minimize:
x1 = MovableSignal("x1", initial_value=0.1)
x2 = MovableSignal("x2", initial_value=0.23)
dofs = [
RangeDOF(actuator=x1, bounds=(-5, 5), parameter_type="float"),
RangeDOF(actuator=x2, bounds=(-5, 5), parameter_type="float"),
]
objectives = [
Objective(name="himmelblau_2d", minimize=True),
]
sensors = []
Writing the evaluation function#
The evaluation function computes objective values from experimental data. Bluesky Adaptive passes it the uid returned by the acquisition plan and the suggestions that were tried. This tutorial uses the default acquisition plan, so the uid is a Bluesky run UID and blop_acquisition_order associates measurements with outcomes.
from collections.abc import Mapping, Sequence
class Himmelblau2DEvaluation:
def __init__(self, tiled_client: Container):
self.tiled_client = tiled_client
def __call__(self, uid: str, suggestions: Sequence[Mapping]) -> Sequence[Mapping]:
run = self.tiled_client[uid]
outcomes = []
acquisition_order = run.start["blop_acquisition_order"]
x1_data = run["primary/x1"].read()
x2_data = run["primary/x2"].read()
for index, suggestion_id in enumerate(acquisition_order):
x1 = x1_data[index]
x2 = x2_data[index]
# Himmelblau function: has four global minima where value = 0
outcomes.append({"himmelblau_2d": (x1**2 + x2 - 11) ** 2 + (x1 + x2**2 - 7) ** 2, "_id": suggestion_id})
return outcomes
Running the optimization#
The Agent brings everything together. Create one with your DOFs, objectives, and evaluation function, then run the optimization:
agent = Scipy.Agent(
sensors=sensors,
dofs=dofs,
objectives=objectives,
evaluation_function=Himmelblau2DEvaluation(tiled_client=tiled_client),
name="simple-experiment",
description="A simple experiment optimizing the Himmelblau function",
)
RE(agent.optimize(10))
╭───────────────────────────────────────────────── Optimization ──────────────────────────────────────────────────╮ │ Optimizer InteractiveOptimizer │ │ Actuators x1, x2 │ │ Sensors N/A │ │ Iterations 10 │ │ Run UID 9b299d9b-f678-4d29-9697-c0f2bf18ab9f │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ ┃ Suggestion ID ┃ x1 ┃ x2 ┃ himmelblau_2d ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ └────────────────────────────┴────────────────────────────┴───────────────────────────┴───────────────────────────┘
┃ ┃ ┃ ┃ ┃ ┃ 0 ┃ 0 ┃ 0 ┃ 170 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 1 ┃ 1e-08 ┃ 0 ┃ 170 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 2 ┃ 0 ┃ 1e-08 ┃ 170 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 3 ┃ 5 ┃ 5 ┃ 890 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 4 ┃ 5 ┃ 5 ┃ 890 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
──────────────────────────────────────────────── Iteration 5 / 10 ─────────────────────────────────────────────────
himmelblau_2d min: 170 max: 890 mean: 458 (5 pts sampled)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
┃ ┃ ┃ ┃ ┃ ┃ 5 ┃ 5 ┃ 5 ┃ 890 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 6 ┃ 1.51545 ┃ 1.51545 ┃ 61.8302 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 7 ┃ 1.51545 ┃ 1.51545 ┃ 61.8302 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 8 ┃ 1.51545 ┃ 1.51545 ┃ 61.8302 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 9 ┃ 3.25772 ┃ 3.25772 ┃ 55.4432 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
──────────────────────────────────────────────── Iteration 10 / 10 ────────────────────────────────────────────────
himmelblau_2d min: 55.4432 max: 890 mean: 342.093 (10 pts sampled)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
Summary Statistics ┏━━━━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━┳━━━━━┳━━━━━━━━━┳━━━━━━━━━┳━━━━━━━┓ ┃ Name ┃ Type ┃ Min ┃ Max ┃ Mean ┃ Std ┃ Count ┃ ┡━━━━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━╇━━━━━╇━━━━━━━━━╇━━━━━━━━━╇━━━━━━━┩ │ x1 │ param │ 0 │ 5 │ 2.28041 │ 2.12132 │ 10 │ │ x2 │ param │ 0 │ 5 │ 2.28041 │ 2.12132 │ 10 │ │ himmelblau_2d │ outcome │ 55.4432 │ 890 │ 342.093 │ 381.119 │ 10 │ └───────────────┴─────────┴─────────┴─────┴─────────┴─────────┴───────┘
────────────────────────────────────────────── Optimization Complete ──────────────────────────────────────────────
('9b299d9b-f678-4d29-9697-c0f2bf18ab9f',
'8721a7e4-c049-4717-a6fd-3451e9e4884e',
'1ac8e15e-75b4-4b76-bd2e-4a0bef85b468',
'bb9d4e05-dc62-4a95-b14e-84930473bca8',
'2eef323a-6e39-480e-abe4-e0b351f4eaaf',
'8993833e-6599-4225-8d13-dd6c8eacc127',
'a17e0bcf-2070-4bb7-aa8c-d53a1ce1cbca',
'9baa8e8a-0d0d-4f25-8cf5-ad40c008f371',
'a9381a7c-7f66-427c-831e-1c81a266ea6f',
'9c355c6c-a0f8-43ef-a9bf-8b9423e69e38',
'a3ca9f39-f03e-42fa-a21c-f29fdf4ccd86')
Configuring the optimization#
Sometimes a default Agent optimization may not do all that you’d like. We expose a configuration object called ScipyCFG and a pure scipy interface so that the classic parameters of scipy minimize can be tweaked (and some multipoint sampling can be used).
config = ScipyCFG(dofs=dofs, objective=objectives[0], optimizer=SCP.DUAL_ANNEALING, threads=4, max_iter=2, eps=0.1)
agent = Scipy(
sensors=sensors,
config=config,
evaluation_function=Himmelblau2DEvaluation(tiled_client=tiled_client),
name="test_experiment",
)
res_uid = RE(agent.optimize(20, n_points=2))
╭───────────────────────────────────────────────── Optimization ──────────────────────────────────────────────────╮ │ Optimizer InteractiveOptimizer │ │ Actuators x1, x2 │ │ Sensors N/A │ │ Iterations 20 Points/iter 2 │ │ Run UID 8fde87bc-6280-430b-a9ef-87025048661f │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────────╯
┏━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┳━━━━━━━━━━━━━━━━━━━━━━━━━━━┓ ┃ Suggestion ID ┃ x1 ┃ x2 ┃ himmelblau_2d ┃ ┡━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━╇━━━━━━━━━━━━━━━━━━━━━━━━━━━┩ └────────────────────────────┴────────────────────────────┴───────────────────────────┴───────────────────────────┘
┃ ┃ ┃ ┃ ┃ ┃ 0 ┃ 0 ┃ 0 ┃ 170 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 1 ┃ -1.45058 ┃ -1.45058 ┃ 147.325 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 2 ┃ -1.22555 ┃ -1.22555 ┃ 160.201 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 3 ┃ -1.33003 ┃ -1.22555 ┃ 155.962 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
/home/runner/work/bluesky-adaptive/bluesky-adaptive/.pixi/envs/docs/lib/python3.13/site-packages/scipy/optimize/_dual_annealing.py:434: OptimizeWarning: Unknown solver options: max_iter
mres = self.minimizer(self.func_wrapper.fun, x, **self.kwargs)
┃ ┃ ┃ ┃ ┃ ┃ 4 ┃ -1.33003 ┃ -4.1982 ┃ 266.738 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
──────────────────────────────────────────────── Iteration 5 / 20 ─────────────────────────────────────────────────
himmelblau_2d min: 147.325 max: 266.738 mean: 180.045 (5 pts sampled)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
┃ ┃ ┃ ┃ ┃ ┃ 5 ┃ -1.45058 ┃ -1.45058 ┃ 147.325 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 6 ┃ -1.35058 ┃ -1.45058 ┃ 151.94 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 7 ┃ -1.45058 ┃ -1.35058 ┃ 148.899 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 8 ┃ -5 ┃ -5 ┃ 250 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 10 ┃ -4.9 ┃ -5 ┃ 235.77 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
──────────────────────────────────────────────── Iteration 9 / 20 ─────────────────────────────────────────────────
himmelblau_2d min: 147.325 max: 266.738 mean: 183.416 (10 pts sampled)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
┃ ┃ ┃ ┃ ┃ ┃ 9 ┃ -5 ┃ -4.9 ┃ 227.05 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 11 ┃ -3.06698 ┃ -3.06698 ┃ 22.1578 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 12 ┃ -3.06698 ┃ -2.96698 ┃ 22.397 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 13 ┃ -2.96698 ┃ -3.06698 ┃ 28.0242 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 14 ┃ -3.77839 ┃ -3.77839 ┃ 12.4869 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
──────────────────────────────────────────────── Iteration 12 / 20 ────────────────────────────────────────────────
himmelblau_2d min: 12.4869 max: 266.738 mean: 143.085 (15 pts sampled)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
┃ ┃ ┃ ┃ ┃ ┃ 15 ┃ -3.67839 ┃ -3.77839 ┃ 14.5014 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 16 ┃ -3.77839 ┃ -3.67839 ┃ 7.73602 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 17 ┃ -4.83504 ┃ -2.33691 ┃ 141.442 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 18 ┃ -4.83504 ┃ -2.23691 ┃ 149.5 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 19 ┃ -4.73504 ┃ -2.33691 ┃ 121.875 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
──────────────────────────────────────────────── Iteration 15 / 20 ────────────────────────────────────────────────
himmelblau_2d min: 7.73602 max: 266.738 mean: 129.067 (20 pts sampled)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
┃ ┃ ┃ ┃ ┃ ┃ 20 ┃ -3.97897 ┃ -3.50475 ┃ 3.46335 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 21 ┃ -3.87897 ┃ -3.50475 ┃ 2.2654 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 22 ┃ -3.97897 ┃ -3.40475 ┃ 2.4139 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 23 ┃ -3.34109 ┃ -2.93846 ┃ 10.6161 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 24 ┃ -3.24109 ┃ -2.93846 ┃ 14.372 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
──────────────────────────────────────────────── Iteration 19 / 20 ────────────────────────────────────────────────
himmelblau_2d min: 2.2654 max: 266.738 mean: 104.578 (25 pts sampled)
───────────────────────────────────────────────────────────────────────────────────────────────────────────────────
┃ ┃ ┃ ┃ ┃ ┃ 25 ┃ -3.34109 ┃ -2.83846 ┃ 12.3765 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
┃ ┃ ┃ ┃ ┃ ┃ 26 ┃ -3.75482 ┃ -3.30575 ┃ 0.072873 ┃ ┡────────────────────────────╇────────────────────────────╇───────────────────────────╇───────────────────────────┩
Summary Statistics ┏━━━━━━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━━━━┳━━━━━━━━━┳━━━━━━━┓ ┃ Name ┃ Type ┃ Min ┃ Max ┃ Mean ┃ Std ┃ Count ┃ ┡━━━━━━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━━━━╇━━━━━━━━━╇━━━━━━━┩ │ x1 │ param │ -5 │ 0 │ -3.13867 │ 1.43737 │ 27 │ │ x2 │ param │ -5 │ 0 │ -2.8494 │ 1.26487 │ 27 │ │ himmelblau_2d │ outcome │ 0.072873 │ 266.738 │ 97.293 │ 90.4417 │ 27 │ └───────────────┴─────────┴──────────┴─────────┴──────────┴─────────┴───────┘
────────────────────────────────────────────── Optimization Complete ──────────────────────────────────────────────
Viewing the results#
Scipy is a local optimizer so it doesn’t have internal point tracking, but we can to grab it from our datastore.
import numpy as np
import matplotlib.pyplot as plt
import pandas as pd
res_client = tiled_client[res_uid[0]]
data = res_client["primary"].read().to_dataframe()
fig, ax = plt.subplots(figsize=(12, 8))
xb, yb = np.random.uniform(-5, 5, (2, 1000))
ax.tripcolor(xb, yb, (xb**2 + yb - 11) ** 2 + (xb + yb**2 - 7) ** 2, shading="gouraud")
ps = ax.scatter(data.x1, data.x2, marker='+', c=range(len(data.x1)), cmap="plasma", s=50)
plt.colorbar(ps).set_label("sample index")
plt.title("Visualizing Scipy's traversal of Himmelblau")
Text(0.5, 1.0, "Visualizing Scipy's traversal of Himmelblau")
Seeing the sample history
data
| iteration | suggestion_ids | x2 | x1 | acquisition_uid | himmelblau_2d | |
|---|---|---|---|---|---|---|
| time | ||||||
| 1.793050e+09 | 0 | 0 | 0.000000 | 0.000000 | 34b9765b-455c-4fc0-91e6-bc67fa3a30fc | 170.000000 |
| 1.793050e+09 | 1 | 1 | -1.450582 | -1.450582 | f7619190-a24e-4b69-a14f-19f29e6eb554 | 147.324608 |
| 1.793050e+09 | 2 | 2 | -1.225555 | -1.225555 | bb06c34f-6741-4353-a105-23000213c94e | 160.201352 |
| 1.793050e+09 | 3 | 3 | -1.225555 | -1.330029 | eb549714-ae79-449f-b152-507480360628 | 155.962222 |
| 1.793050e+09 | 4 | 4 | -4.198197 | -1.330029 | 8677bc68-5cf2-4e5c-84d4-e8b28c14a8ea | 266.737897 |
| 1.793050e+09 | 5 | 5 | -1.450582 | -1.450582 | 83883022-0d33-4583-b9ae-abe12e403902 | 147.324608 |
| 1.793050e+09 | 6 | 6 | -1.450582 | -1.350582 | 2c336447-6d5f-40b1-ae4d-03c5ed8ad2a2 | 151.940182 |
| 1.793050e+09 | 6 | 7 | -1.350582 | -1.450582 | 2c336447-6d5f-40b1-ae4d-03c5ed8ad2a2 | 148.899251 |
| 1.793050e+09 | 7 | 8 | -5.000000 | -5.000000 | c8df5901-e367-4331-87c2-4647a8728460 | 250.000000 |
| 1.793050e+09 | 8 | 10 | -5.000000 | -4.900000 | d47dfaac-57f5-4357-bace-2ec947ad8f67 | 235.770100 |
| 1.793050e+09 | 8 | 9 | -4.900000 | -5.000000 | d47dfaac-57f5-4357-bace-2ec947ad8f67 | 227.050100 |
| 1.793050e+09 | 9 | 11 | -3.066978 | -3.066978 | fe904a09-353f-4912-9a99-105e10e3e34c | 22.157844 |
| 1.793050e+09 | 10 | 12 | -2.966978 | -3.066978 | e24839a0-5cc5-437e-9da1-10564cb64dfa | 22.397041 |
| 1.793050e+09 | 10 | 13 | -3.066978 | -2.966978 | e24839a0-5cc5-437e-9da1-10564cb64dfa | 28.024206 |
| 1.793050e+09 | 11 | 14 | -3.778386 | -3.778386 | 78bd4773-1fb7-4101-8f18-5ce0a86ac5d3 | 12.486905 |
| 1.793050e+09 | 12 | 15 | -3.778386 | -3.678386 | 075849e1-7bc7-4cdf-bed0-1e3c06157a4b | 14.501437 |
| 1.793050e+09 | 12 | 16 | -3.678386 | -3.778386 | 075849e1-7bc7-4cdf-bed0-1e3c06157a4b | 7.736019 |
| 1.793050e+09 | 13 | 17 | -2.336910 | -4.835040 | c93b59fb-37ea-4fe5-97a4-e1192506f1df | 141.442263 |
| 1.793050e+09 | 14 | 18 | -2.236910 | -4.835040 | 94b37190-0bd6-4760-abd9-dc5a28691383 | 149.500209 |
| 1.793050e+09 | 14 | 19 | -2.336910 | -4.735040 | 94b37190-0bd6-4760-abd9-dc5a28691383 | 121.875275 |
| 1.793050e+09 | 15 | 20 | -3.504746 | -3.978975 | fdf129ec-0648-4891-970b-6f5263f21d7e | 3.463352 |
| 1.793050e+09 | 16 | 21 | -3.504746 | -3.878975 | 76ea998b-d427-4746-9032-f1e34446fee7 | 2.265404 |
| 1.793050e+09 | 16 | 22 | -3.404746 | -3.978975 | 76ea998b-d427-4746-9032-f1e34446fee7 | 2.413897 |
| 1.793050e+09 | 17 | 23 | -2.938459 | -3.341090 | 27356e88-ba32-479a-8df5-9f8236aeb015 | 10.616147 |
| 1.793050e+09 | 18 | 24 | -2.938459 | -3.241090 | 92f4f986-c290-4904-933c-e79562dd9d18 | 14.371958 |
| 1.793050e+09 | 18 | 25 | -2.838459 | -3.341090 | 92f4f986-c290-4904-933c-e79562dd9d18 | 12.376479 |
| 1.793050e+09 | 19 | 26 | -3.305747 | -3.754815 | 95cbd0fb-c105-4dc6-ad60-af82b97b814e | 0.072873 |
print(agent.get_best_points())
[22, {'x1': np.float64(-3.7548153874739545), 'x2': np.float64(-3.305746617949284)}, {'himmelblau_2d': np.float64(3.463352404930271)}]
The Himmelblau function has four global minima (all with value 0). The summarize output shows which one(s) the optimizer found.
What you learned#
You now understand the three core concepts of Bluesky Adaptive:
DOFs: The parameters the optimizer adjusts (here,
x1andx2with bounds)Objectives: What you’re optimizing (here, minimizing the Himmelblau function)
Agent: Coordinates the optimization loop between Bluesky and the evaluation function
Next steps#
For a more comprehensive tutorial with multiple objectives and diagnostic tools, see Optimizing KB Mirrors.