Commit b2416c0b authored by  Eivinas  Butkus's avatar Eivinas Butkus

Update README.md

parent 1645c4b7
......@@ -4,11 +4,19 @@ Behaviour Descriptor's" (Eivinas Butkus)
The code archive includes all the best version of each DR technique (PCA, Autoencoder,
UMAP and betaVAE) from the hexapod experiment as well as Manual Definition and Random BDs.
Dependency: Singularity.
To run any of the experiments:
1. `cd` into the relevant experiment's `singularity` folder.
2. Run `./build_final_image.sh` and there will appear a Singularity image with a name like `final_pca_2019-09-05_12_33_40.simg`.
3. Simply run the image as an executable to start the experiment (e.g. `./final_pca_2019-09-05_12_33_40.simg`).
2. Run `./build_final_image.sh` and there will appear a Singularity image with a name like `final_manual_definition_2019-09-05_13_26_59.simg`.
3. Simply run the image as an executable to start the experiment (e.g. `./final_manual_definition_2019-09-05_13_26_59.simg`).
Two important notes:
1. In the case of PCA and UMAP, please run the experiment using `singularity run --bind model:/git/sferes2/model NAME_OF_THE_IMAGE.simg`.
2. In the case of AE and betaVAE, you can use GPU support with `singularity run --nv NAME_OF_THE_IMAGE.simg`.
Results can be found in `singularity/results` of the experiment.
This work has been done at the Adaptive and Intelligent Robotics Lab (AIRL)
which is directed by Antoine Cully. The experiments are based on the AIRL development environment
and the code was adapted from previous AURORA and QD experiments designed by Antoine Cully.
\ No newline at end of file
and the code was adapted from previous AURORA and QD experiments from this environment.
\ No newline at end of file
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment