MO-Gym: A Library of Multi-Objective Reinforcement Learning Environments

2022-11-30Benelux Conference on Artificial Intelligence BNAIC/BeNeLearn 2022Code Available2· sign in to hype

Lucas N. Alegre, Florian Felten, El-Ghazali Talbi, Grégoire Danoy, Ann Nowé, Ana L. C. Bazzan, Bruno C. da Silva

Code Available — Be the first to reproduce this paper.

Code

github.com/Farama-Foundation/MO-Gymnasium
Officialnone★ 375
github.com/lucasalegre/mo-gym
OfficialIn papernone★ 0

Abstract

We introduce MO-Gym, 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. MO-Gym is available at: https://github.com/LucasAlegre/mo-gym.

Tasks

Multi-Objective Reinforcement Learning OpenAI Gym reinforcement-learning Reinforcement Learning Reinforcement Learning (RL)

MO-Gym: A Library of Multi-Objective Reinforcement Learning Environments

Code

Abstract

Tasks

Reproductions