Skip to content
Safe Exploration with MPC and Gaussian process models
Branch: master
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Type Name Latest commit message Commit time
Failed to load latest commit information.
.circleci Run circleCI weekly May 13, 2019
experiments cleaned up unused import, fixed import May 13, 2019
safe_exploration
scripts Test style, but ignore all of the broken ones Jan 25, 2019
.dockerignore Initial testing framework Jan 16, 2019
.gitignore Fix test Dec 14, 2018
.travis.yml
Dockerfile
LICENSE Initial commit Dec 6, 2018
README.rst Add build badges May 13, 2019
conftest.py
setup.cfg changed code coverage settings Feb 25, 2019
setup.py Restrict torch version May 11, 2019

README.rst

Learning-based Model Predictive Control for Safe Exploration

https://circleci.com/gh/befelix/safe-exploration/tree/master.svg?style=svg https://travis-ci.com/befelix/safe-exploration.svg?branch=master

This code accompanies the following paper:

[1]T. Koller, F. Berkenkamp, M. Turchetta, A. Krause, Learning-based Model Predictive Control for Safe Exploration in Proc. of the Conference on Decision and Control (CDC), 2018

Installation

Install the library including all dependencies with.

pip install -e ".[test,visualization,ssm_gpy,ssm_pytroch]"

test for the testing tools. visualization for visualizations such as matplotlib. ssm_gpy and ssm_pytorch for state space models based on GPy or PyTorch, respectively.

Experiments can be run using the experiments/run.py script.

Test can be run using pytest. There are also more sophisticated style tests in scripts/test_code.sh.

You can’t perform that action at this time.