mlsanityData to 14 Oct 2026

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

arXiv 2603.09237 ↗First posted 10 Mar 2026cs.ROcited by 2

On the map: Deep reinforcement learning methods → RL for games and combinatorial optimization

Abstract (arXiv)

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.

Key facts. Cited by 2 papers in the map (data through 14 Oct 2026). Placed in RL for games and combinatorial optimization, one of 15 directions in Deep reinforcement learning methods. Builds on 25 of its 36 references that are in the map. First posted on arXiv 10 Mar 2026.

Builds on

25 of 36 references.

Closest ancestors · 1

Same direction, newest first

  1. 2025Pareto Set Learning for Multi-Objective Reinforcement Learning12 Jan

Other references · 24

  1. 2017Proximal Policy Optimization Algorithmscited by 15,215
  2. 2018Soft Actor-Critic: Off-Policy Maximum Entropy Deep Reinforcement Learning with a Stochastic Actorcited by 4,885
  3. 2016OpenAI Gymcited by 1,736
  4. 2016HyperNetworkscited by 1,027
  5. 2021Learning to Walk in Minutes Using Massively Parallel Deep Reinforcement Learningcited by 512
  6. 2019Learning agile and dynamic motor skills for legged robotscited by 504
  7. 2021Brax -- A Differentiable Physics Engine for Large Scale Rigid Body Simulationcited by 407
  8. 2020dm_control: Software and Tasks for Continuous Controlcited by 375
  9. 2021A Practical Guide to Multi-Objective Reinforcement Learning and Planningcited by 256
  10. 2020pymoo: Multi-objective Optimization in Pythoncited by 200
  11. 2025BeyondMimic: From Motion Tracking to Versatile Humanoid Control via Guided Diffusioncited by 165
  12. 2025MuJoCo Playgroundcited by 78
12 more
  1. 2022PD-MORL: Preference-Driven Multi-Objective Reinforcement Learning Algorithmcited by 58
  2. 2024Opt2Skill: Imitating Dynamically-feasible Whole-Body Trajectories for Versatile Humanoid Loco-Manipulationcited by 39
  3. 2019Preference-Based Learning for Exoskeleton Gait Optimizationcited by 24
  4. 2020ROIAL: Region of Interest Active Learning for Characterizing Exoskeleton Gait Preference Landscapescited by 20
  5. 2023EvoX: A Distributed GPU-accelerated Framework for Scalable Evolutionary Computationcited by 18
  6. 2016A First Look at Ad-block Detection: A New Arms Race on the Webcited by 16
  7. 2023Rating-based Reinforcement Learningcited by 15
  8. 2025AMOR: Adaptive Character Control through Multi-Objective Reinforcement Learningcited by 9
  9. 2024Learning Pareto Set for Multi-Objective Continuous Robot Controlcited by 8
  10. 2025Studying the Interplay Between the Actor and Critic Representations in Reinforcement Learningcited by 8
  11. 2025NaviGait: Navigating Dynamically Feasible Gait Libraries using Deep Reinforcement Learningcited by 2
  12. 2023A Learning-Based Framework for Safe Human-Robot Collaboration with Multiple Backup Control Barrier Functionscited by 1

Built on by

Cited by year (2026 to 14 Oct)

Citing papers per year: 2026: 2.

2 papers.

  1. 2026A GPU-Parallel Framework for Heterogeneous Multi-Task Reinforcement Learningcited by 0
  2. 2026MOCHA: Multi-Objective Co-Design using Hypernetwork Architecturescited by 0

Similar, not cited

Close in wording, no citation either way

  1. 2025Benchmarking MOEAs for solving continuous multi-objective RL problems
  2. 2024C-MORL: Multi-Objective Reinforcement Learning through Efficient Discovery of Pareto Front
  3. 2025Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks
  4. 2025Isaac Lab: A GPU-Accelerated Simulation Framework for Multi-Modal Robot Learning
  5. 2025Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots
  6. 2025Scalable Multi-Objective Robot Reinforcement Learning through Gradient Conflict Resolution
  7. 2023Scaling Pareto-Efficient Decision Making Via Offline Multi-Objective RL
  8. 2026PA2D-MORL: Pareto Ascent Directional Decomposition based Multi-Objective Reinforcement Learning