Installation

SmartCer requires Python 3.12 or newer. The runtime dependencies are gymnasium, numpy, pandas and holidays.

From PyPI

pip install smartcer
# with Stable-Baselines3, for the training example and the results callback
pip install "smartcer[rl]"

From source

A source checkout also gives access to the synthetic example scenario used in the quickstart.

git clone https://github.com/unisi-lab305/SmartCer
cd SmartCer
pip install -e .          # plain editable installation
pip install -e .[all]     # tests, lint tools and Stable-Baselines3
make test

To install a tagged release directly from GitHub:

pip install git+https://github.com/unisi-lab305/SmartCer@v1.0.1

Environment registration

The environment ID is SmartCer-v1. It is registered when smartcer is imported:

import gymnasium as gym
import smartcer  # registers SmartCer-v1

env = gym.make('SmartCer-v1', scenario='path/to/scenario')

With Gymnasium 1.0 or newer, import smartcer before gym.make, or use gym.make('smartcer:SmartCer-v1', ...).

Building these docs

pip install -e ".[docs]"
sphinx-build -W --keep-going -b html docs docs/_build/html

Then open docs/_build/html/index.html.