About us

Consortium

Team

AI Flanders

Contact

<h5>Description:</h5>
<p>MO-Gym is an extensible library containing a diverse set of multi-objective reinforcement learning environments. It introduces a standardized API that facilitates conducting experiments and performance analyses of algorithms designed to interact with multi-objective Markov decision processes. Importantly, it extends the widely-used OpenAI Gym API, allowing the reuse of algorithms and features that are well-established in the reinforcement learning community.</p>

<h5>More Information:</h5>
<ul>
<li><strong>Grand Challenge/Workpackage(s)</strong>: GC3 - WP2</li>
<li><strong>Responsible Research Lead</strong>: <a href="mailto:lucasnale@gmail.com" target="_blank" rel="noopener">Lucas N. Alegre</a>&nbsp;</li>
<li><strong>Authors</strong>: <a href="mailto:lucasnale@gmail.com" target="_blank" rel="noopener">Lucas N. Alegre</a>, <a href="mailto:florian.felten@uni.lu" target="_blank" rel="noopener">Florian Felten</a></li>
<li><strong>Programming Language</strong>: Python</li>
<li><a href="https://github.com/LucasAlegre/mo-gym" target="_blank" rel="noopener">Link to the repository</a></li>
<li><a href="https://www.youtube.com/watch?v=g2qdKkwKrlw" target="_blank" rel="noopener">Link to video</a></li>
<li><strong>Categories:</strong> Reinforcement learning</li>
</ul>

<h5>Publications:</h5>
<ul>
<li>Lucas N. Alegre, Florian Felten, El-Ghazali Talbi, Gr&eacute;goire Danoy, Ann Now&eacute;, Ana L. C. Bazzan, and Bruno C. da Silva. 2022. <a href="https://bnaic2022.uantwerpen.be/wp-content/uploads/BNAICBeNeLearn_2022_submission_6485.pdf" target="_blank" rel="noopener">MO-Gym: A Library of Multi-Objective Reinforcement Learning Environments</a>. In Proceedings of the 34th Benelux Conference on Artificial Intelligence BNAIC/Benelearn 2022.</li>
</ul>