This is the code repository accompanying the paper LTL2Action: Generalizing LTL Instructions for Multi-Task RL, which will appear in ICML 2021.
In the animation below, our agent's behaviour, compared to a myopic one is demonstrated on ZoneEnv
, a custom environment based on OpenAI's SafetyGym:
We recommend using Python 3.6 to run this code.
pip install -r requirements.txt
- Install Spot-2.9
- Follow the installation instructions at the link. Spot should be installed in
/usr/local/lib/python3.6/site-packages/spot
. This step usually takes around 20 mins.
- Follow the installation instructions at the link. Spot should be installed in
- (Optional) To run the OpenAI Safety Gym, you will need Mujoco installed, as well as an active license.
pip install mujoco-py==2.0.2.9
pip install -e src/envs/safety/safety-gym/
Instructions for training and evaluating RL agents on each of our domains is available in the src
folder.
@article{DBLP:journals/corr/abs-2102-06858,
author = {Pashootan Vaezipoor and
Andrew C. Li and
Rodrigo Toro Icarte and
Sheila A. McIlraith},
title = {LTL2Action: Generalizing {LTL} Instructions for Multi-Task {RL}},
journal = {CoRR},
volume = {abs/2102.06858},
year = {2021},
url = {https://arxiv.org/abs/2102.06858},
archivePrefix = {arXiv},
eprint = {2102.06858},
timestamp = {Thu, 18 Feb 2021 15:26:00 +0100},
biburl = {https://dblp.org/rec/journals/corr/abs-2102-06858.bib},
bibsource = {dblp computer science bibliography, https://dblp.org}
}