Code for 'Autonomous Reuse of Motor Exploration Trajectories' article.
Switch branches/tags
Nothing to show
Clone or download
Fetching latest commit…
Cannot retrieve the latest commit at this time.
Permalink
Failed to load latest commit information.
bias
exp/l2l
explib
submodules
tests
.gitignore
.gitmodules
license.txt
readme.md

readme.md

This repository holds the code used to run the experiments presented in the article Autonomous Reuse of Motor Exploration Trajectories.

Using this code, you can reproduce the graphs presented in the article from scratch, and examine any and all of the way they were produced.

It is not intended as being fit for any purpose other than scientific.

OpenScience License

This software is placed under the OpenScience license, which is the LGPL, with the additional condition that if you publish scientific results using this code, you have to publish the corresponding modifications of the code.

If you publicly release any scientific claims or data that were supported or generated by the Program or a modification thereof, in whole or in part, you will release any modifications you made to the Program. This License will be in effect for the modified program.

Installation

  1. Install pypubsub, scipy, treedict, cython, pandas and eigen.
    • pip install pypubsub scipy treedict cython pandas
  2. Get the code
  3. Install submodules
    • git submodule init
    • git submodule update
    • install each submodule according to its readme.md.

Usage

  1. Edit paths in file explib/run/paths.py to suit your folder structure, and create each of the listed folde
  2. Go to exp/l2l
  3. Run ./l2l_missing.py -r. This will generate and display the file missing.sh. This is the list of command that need to be run.
  4. Run ./l2l_run.py.
  5. Wait for all command to finish (it may take a month if run sequentially: use a cluster, the code automatically switches to use the qsub command if it exits. You may also want to limit the number of time the experiment is reapeated (default 20))
  6. Redo step 3 and 4 until missing.sh is empty.
  7. Run ./l2l_graphs.py

Although some care has been taken to make the code usable, it might not be. Don't hesitate to submit an issue or make a pull request.