Simple building control environments for reinforcement learning.
Project description
Warning
Bauwerk is in a very early stage of development, not stable at the moment and not recommended for general usage at this point. Use at your own risk.
bauwerk
Super simple building control environments for reinforcement learning.
Free software: MIT license
Documentation: https://bauwerk.readthedocs.io.
Features
TODO
Credits
This package was created with Cookiecutter and the audreyr/cookiecutter-pypackage project template.
History
0.2.2 (2022-10-26)
Features
Add experiment script
Add extensive evaluation features
Add support for much slower speed in game widget
Add benchmarks
Add support for setting tasks in environment
Add wrappers:
that add task parameters to observation space.
that clip the reward
that clip the action space
that normalise observation space
Improvements
Add clock and day to game widget
Design improvements for game widget
Action spaces dtype can now be set in env cfg
0.2.1 (2022-09-12)
Features
Add time_of_day variable to observation space.
Improvements
The solve function is now directly imported with bauwerk, to simplify usage.
Additional sections added to documentation.
Add more grid parameters to SolarBatteryHouseEnv configuration.
Fixes:
Ensure solver outputs actions that are valid in environment (i.e. normalised)
0.2.0 (2022-09-09)
Features:
Add game widget based on SolarBatteryHouseEnv.
Includes browser-based version of Bauwerk game that can be played by anybody without installing anything.
Add support for selling to the grid in SolarBatteryHouseEnv.
Improvements:
Add explicit CVXPY-based solver in bauwerk.envs.solvers for SolarBatteryHouseEnv that was missing earlier.
Update SolarBatteryHouseEnv to comply with new gym step API by returning truncated value.
Add automatic github-actions-based testing of package.
0.1.0 (2022-08-12)
First release on PyPI.
Features:
SolarBatteryHouseEnv: a simple environment representing a single family home with a solar photovoltaic installations and a home battery that can be controlled.
Optional integration with CVXPY to compute optimal actions in Bauwerk environments.
Project details
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
Built Distribution
File details
Details for the file bauwerk-0.3.0.tar.gz
.
File metadata
- Download URL: bauwerk-0.3.0.tar.gz
- Upload date:
- Size: 607.7 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.9.15
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | 9ef5d9279caea3a8de86199a224b936373810c851b05bf2641b8a9b570025bd8 |
|
MD5 | 0fbf493687647f90782992a63e3f5a94 |
|
BLAKE2b-256 | 99c4912cd8ffd5a16ce9e1cc103b874cfcc7d58ec2372d3babd695fd90065005 |
File details
Details for the file bauwerk-0.3.0-py2.py3-none-any.whl
.
File metadata
- Download URL: bauwerk-0.3.0-py2.py3-none-any.whl
- Upload date:
- Size: 216.6 kB
- Tags: Python 2, Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.9.15
File hashes
Algorithm | Hash digest | |
---|---|---|
SHA256 | f1c8b8a7473ef779eb517e7d6fd64ffb1f56006939a9af093351f4b7d7aee375 |
|
MD5 | 2e759a4660f1a6b1ebfeb0294a83ac89 |
|
BLAKE2b-256 | 418bf98041ba34be6c4c321b357d4968f92e2c9f7d41106bd8cd9b23e682d04b |