temprl 0.2.2

Framework for Reinforcement Learning with Temporal Goals.

# TempRL

[](https://pypi.python.org/pypi/temprl) [](https://travis-ci.org/sapienza-rl/temprl) [](https://pypi.python.org/pypi/temprl) [](https://coveralls.io/github/sapienza-rl/temprl?branch=master) [](https://img.shields.io/badge/flake8-checked-blueviolet) [](https://img.shields.io/badge/mypy-checked-blue) [](https://img.shields.io/badge/license-Apache%202-lightgrey)

Framework for Reinforcement Learning with Temporal Goals defined by LTLf/LDLf formulas.

## Install

Install from master branch:

• with pip:

  pip3 install git+https://github.com/sapienza-rl/temprl.git

• or, clone the repository and install:

  git clone htts://github.com/sapienza-rl/temprl.git cd temprl pip install .

## Tests

To run the tests:

tox

To run only the code style checks:

tox -e flake8

## Docs

To build the docs:

mkdocs build

To view documentation in a browser

mkdocs serve

and then go to [http://localhost:8000](http://localhost:8000)

## License

Copyright 2018-2019 Marco Favorito

# History

## 0.1.0 (2018-04-04)

• First release on PyPI.

## 0.2.0 (2019-07-13)

• Main refactoring of the package.

## 0.2.1 (2019-11-03)

• Improved testing and continuous integration.

• Fixed minor bugs and issues.

## 0.2.2 (2019-11-03)

• Improved support for reward shaping.

• Fixed minor bugs and issues.