/metastable-baselines

Github Mirror for Metastable Baselines

Primary LanguagePython

Metastable Baselines

During training of a RL-Agent we follow the gradient of the loss, which leads us to a minimum. In cases where the found minimum is merely a local minimum, this can be seen as a false vacuum in our loss space. Exploration mechanisms try to let our training procedure escape these stable states: Making them metastable.

In order to archive this, this Repo contains some extensions for Stable Baselines 3 by DLR-RM
These extensions include:

The resulting algorithms can than be tested for their ability of exploration in the enviroments provided by Project Columbus

This Repo was created as part of my bachelor-thesis at ALR (KIT).

Installation

(optional) Columbus for test.py and replay.py

Install Project Columbus by following the instructions in the repo.

Install dependency: Metastable Projections

Follow instructions for the Public Version (GitHub Mirror) / Private Version (GitHub Mirror). The private version also requires ALR's ITPAL as a dependency. Only the private version supports KL Projections.

Install as a package

Then install this repo as a package:

pip install -e .

License

Since this Repo is an extension to Stable Baselines 3 by DLR-RM, it contains some of it's code. SB3 is licensed under the MIT-License.