paper-with-me

Papers

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

2026-03-10 · Neil Janwani, Ellen Novoseller, Vernon J. Lawhern, Maegan Tucker 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.

📄 PDF Abstract BibTeX arXiv:2603.09237

Code (0)

등록된 구현이 없습니다.

Tasks

Reinforcement Learning

Similar Papers 제목 키워드 기반

Benchmarking Massively Parallelized Multi-Task Reinforcement Learning for Robotics Tasks

2025-07-31 · Viraj Joshi, Zifan Xu, Bo Liu, Peter Stone 외 arxiv

Multi-task Reinforcement Learning (MTRL) has emerged as a critical training paradigm for applying reinforcement learning (RL) to a set of complex real-world robotic tasks, which demands a generalizable and robust policy.…

Reinforcement Learning

GS-Playground: A High-Throughput Photorealistic Simulator for Vision-Informed Robot Learning

2026-04-28 · Yufei Jia, Heng Zhang, Ziheng Zhang, Junzhe Wu 외 arxiv

Embodied AI research is undergoing a shift toward vision-centric perceptual paradigms. While massively parallel simulators have catalyzed breakthroughs in proprioception-based locomotion, their potential remains largely …

Unity RL Playground: A Versatile Reinforcement Learning Framework for Mobile Robots

2025-03-07 · Linqi Ye, Rankun Li, Xiaowen Hu, Jiayi Li 외

This paper introduces Unity RL Playground, an open-source reinforcement learning framework built on top of Unity ML-Agents. Unity RL Playground automates the process of training mobile robots to perform various locomotio…

Unity

Tracking Control for a Spherical Pendulum via Curriculum Reinforcement Learning

2023-09-25 · Pascal Klink, Florian Wolf, Kai Ploeger, Jan Peters 외

Reinforcement Learning (RL) allows learning non-trivial robot control laws purely from data. However, many successful applications of RL have relied on ad-hoc regularizations, such as hand-crafted curricula, to regulariz…

reinforcement-learningReinforcement LearningReinforcement Learning (RL)State Estimation

MDP Playground: An Analysis and Debug Testbed for Reinforcement Learning

2019-09-17 · Raghu Rajan, Jessica Lizeth Borja Diaz, Suresh Guttikonda, Fabio Ferreira 외

We present MDP Playground, a testbed for Reinforcement Learning (RL) agents with dimensions of hardness that can be controlled independently to challenge agents in different ways and obtain varying degrees of hardness in…

MuJoCoOpenAI Gymreinforcement-learningReinforcement Learning+1