Getting Started

Installation

To install AlphaCube, open a terminal and run the following command:

pip install -U alphacube

Usage

Basic

Using AlphaCube in Python is simple. The first time alphacube.load() is called, the required model data will be downloaded and cached.

import alphacube

# Загрузка предварительно обученной модели
# По умолчанию "small" для CPU, "large" для GPU
alphacube.load()

# Сборка кубика по заданному скрамблу
result = alphacube.solve(
    scramble="D U F2 L2 U' B2 F2 D L2 U R' F' D R' F' U L D' F' D R2",
    beam_width=1024,
)
print(result)

Вывод

{
    'solutions': [
        "D L D2 R' U2 D B' D' U2 B U2 B' U' B2 D B2 D' B2 F2 U2 F2"
    ],
    'num_nodes': 19744,        # Всего исследованных узлов поиска
    'time': 1.4068585219999659 # Время в секундах
}

Improving Solution Quality

If you want shorter solutions, increase the beam_width parameter. This makes the search more exhaustive at the cost of more computation time.

result = alphacube.solve(
    scramble="D U F2 L2 U' B2 F2 D L2 U R' F' D R' F' U L D' F' D R2",
    beam_width=65536,
)
print(result)

Вывод

{
    'solutions': [
        "D' R' D2 F' L2 F' U B F D L D' L B D2 R2 F2 R2 F'",
        "D2 L2 R' D' B D2 B' D B2 R2 U2 L' U L' D' U2 R' F2 R'"
    ],
    'num_nodes': 968984,
    'time': 45.690575091997744
}

Allowing A Few Extra Moves

You can obtain not just the shortest solutions but also slightly longer ones, using the extra_depths parameter. This instructs the solver to continue searching after the first solution is found.

alphacube.load()  # model_id="small"
result = alphacube.solve(
    scramble="D U F2 L2 U' B2 F2 D L2 U R' F' D R' F' U L D' F' D R2",
    beam_width=65536,
    extra_depths=1
)
print(result)

Вывод

{
    'solutions': [
        "D' R' D2 F' L2 F' U B F D L D' L B D2 R2 F2 R2 F'",
        "D2 L2 R' D' B D2 B' D B2 R2 U2 L' U L' D' U2 R' F2 R'",
        "D R F2 L' U2 R2 U2 R2 B2 U' F B2 D' F' D' R2 F2 U F2 L2",  # дополнительно
        "L' D' R' D2 L B' U F2 U R' U' F B' R2 B R B2 F D2 B",      # дополнительно
        "R' F L2 D R2 U' B' L' U2 F2 U L U B2 U2 R2 D' U B2 R2",    # дополнительно
        "L' U' F' R' U D B2 L' B' R' B U2 B2 L2 D' R2 U' D R2 U2"   # дополнительно
    ],
    'num_nodes': 1100056,
    'time': 92.809575091997744
}

GPU Acceleration

If you have a compatible GPU or Mac, you can get a significant speedup by loading a large model.

alphacube.load(model_id="large")
result = alphacube.solve(
    scramble="D U F2 L2 U' B2 F2 D L2 U R' F' D R' F' U L D' F' D R2",
    beam_width=65536,
)
print(result)

Вывод

{
    'solutions': ["D F L' F' U2 B2 U F' L R2 B2 U D' F2 U2 R D'"],
    'num_nodes': 903448,
    'time': 20.46845487099995
}

Applying Ergonomic Bias

To find solutions that are easier to execute manually, provide an ergonomic_bias dictionary to the solve method. Each move is assigned a score, where higher scores indicate more desirable moves. This also enables wide moves like u and r.

ergonomic_bias = {
    "U": 0.9,   "U'": 0.9,  "U2": 0.8,
    "R": 0.8,   "R'": 0.8,  "R2": 0.75,
    "L": 0.55,  "L'": 0.4,  "L2": 0.3,
    "F": 0.7,   "F'": 0.6,  "F2": 0.6,
    "D": 0.3,   "D'": 0.3,  "D2": 0.2,
    "B": 0.05,  "B'": 0.05, "B2": 0.01,
    "u": 0.45,  "u'": 0.45, "u2": 0.4,
    "r": 0.3,   "r'": 0.3,  "r2": 0.25,
    "l": 0.2,   "l'": 0.2,  "l2": 0.15,
    "f": 0.35,  "f'": 0.3,  "f2": 0.25,
    "d": 0.15,  "d'": 0.15, "d2": 0.1,
    "b": 0.03,  "b'": 0.03, "b2": 0.01
}

result = alphacube.solve(
    scramble="D U F2 L2 U' B2 F2 D L2 U R' F' D R' F' U L D' F' D R2",
    beam_width=65536,
    ergonomic_bias=ergonomic_bias
)
print(result)

Вывод

{
    'solutions': [
        "u' U' f' R2 U2 R' L' F' R D2 f2 R2 U2 R U L' U R L",
        "u' U' f' R2 U2 R' L' F' R D2 f2 R2 U2 R d F' U f F",
        "u' U' f' R2 U2 R' L' F' R u2 F2 R2 D2 R u f' l u U"
    ],
    'num_nodes': 1078054,
    'time': 56.13087955299852
}

Models & Trade-Off

AlphaCube offers three compute-optimally trained models from the original paper: "small", "base", and "large".

While larger models are more accurate, the best choice depends on your hardware.

• На CPU модель "small" часто является наиболее эффективным выбором по времени.
• На GPU модель "large" демонстрирует наивысшую производительность и находит лучшие решения за кратчайшее время.

CLI Option

If you prefer using alphacube from the command line, you can do so:

alphacube \
    --model_id large \
    --scramble "F U2 L2 B2 F U L2 U R2 D2 L' B L2 B' R2 U2" \
    --beam_width 100000 \
    --extra_depths 3 \
    --verbose

With abbreviated flags,

alphacube \
    -m large \
    -s "F U2 L2 B2 F U L2 U R2 D2 L' B L2 B' R2 U2" \
    -bw 100000 \
    -ex 3 \
    -v

Please find more details at API Reference > CLI.

Note: The CLI loads the specified model for every execution, making it best suited for single-use commands rather than repeated solving in a script.