MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics

Fuente: arXiv
Saved in:
Bibliographic Details
Main Authors: Janwani, Neil, Novoseller, Ellen, Lawhern, Vernon J., Tucker, Maegan
Format: Preprint
Published: 2026
Subjects:
Online Access:
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866912958355865600
author Janwani, Neil
Novoseller, Ellen
Lawhern, Vernon J.
Tucker, Maegan
author_facet Janwani, Neil
Novoseller, Ellen
Lawhern, Vernon J.
Tucker, Maegan
contents Multi-objective reinforcement learning (MORL) is a powerful tool to learn Pareto-optimal policy families across conflicting objectives. However, unlike traditional RL algorithms, existing MORL algorithms do not effectively leverage large-scale parallelization to concurrently simulate thousands of environments, resulting in vastly increased computation time. Ultimately, this has limited MORL's application towards complex multi-objective robotics problems. To address these challenges, we present 1) MORLAX, a new GPU-native, fast MORL algorithm, and 2) MO-Playground, a pip-installable playground of GPU-accelerated multi-objective environments. Together, MORLAX and MO-Playground approximate Pareto sets within minutes, offering 25-270x speed-ups compared to legacy CPU-based approaches whilst achieving superior Pareto front hypervolumes. We demonstrate the versatility of our approach by implementing a custom BRUCE humanoid robot environment using MO-Playground and learning Pareto-optimal locomotion policies across 6 realistic objectives for BRUCE, such as smoothness, efficiency and arm swinging.
format Preprint
id arxiv_https___arxiv_org_abs_2603_09237
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics
Janwani, Neil
Novoseller, Ellen
Lawhern, Vernon J.
Tucker, Maegan
Robotics
Multi-objective reinforcement learning (MORL) is a powerful tool to learn Pareto-optimal policy families across conflicting objectives. However, unlike traditional RL algorithms, existing MORL algorithms do not effectively leverage large-scale parallelization to concurrently simulate thousands of environments, resulting in vastly increased computation time. Ultimately, this has limited MORL's application towards complex multi-objective robotics problems. To address these challenges, we present 1) MORLAX, a new GPU-native, fast MORL algorithm, and 2) MO-Playground, a pip-installable playground of GPU-accelerated multi-objective environments. Together, MORLAX and MO-Playground approximate Pareto sets within minutes, offering 25-270x speed-ups compared to legacy CPU-based approaches whilst achieving superior Pareto front hypervolumes. We demonstrate the versatility of our approach by implementing a custom BRUCE humanoid robot environment using MO-Playground and learning Pareto-optimal locomotion policies across 6 realistic objectives for BRUCE, such as smoothness, efficiency and arm swinging.
title MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics
topic Robotics
url https://arxiv.org/abs/2603.09237