MO-Playground: 多目标强化学习的大规模并行化方法用于机器人学
MO-Playground: Massively Parallelized Multi-Objective Reinforcement Learning for Robotics
AI总结：
MO-Playground通过GPU加速的多目标环境和MORLAX算法，实现大规模并行化多目标强化学习，显著提升复杂机器人任务中的帕累托最优策略学习效率。
摘要：
多目标强化学习（MORL）是一种强大的工具，用于在冲突目标之间学习帕累托最优策略族。然而，与传统RL算法不同，现有的MORL算法并未有效利用大规模并行化来同时模拟成千上万个环境，导致计算时间大幅增加。最终，这限制了MORL在复杂多目标机器人问题中的应用。为了解决这些挑战，我们提出了1）MORLAX，一种新的GPU原生、快速的MORL算法，以及2）MO-Playground，一个可安装的GPU加速多目标环境游乐场。共同，MORLAX和MO-Playground在几分钟内近似帕累托集，相比传统CPU方法提供了25-270倍的速度提升，同时实现了更优的帕累托前沿超体积。我们通过使用MO-Playground实现一个定制的BRUCE人形机器人环境，并在6个现实目标上学习帕累托最优的运动策略，例如平滑性、效率和手臂摆动。
英文摘要：
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, thus facing vastly increased computation time. Ultimately, this has limited the application of MORL 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 26-271x speed-ups compared to legacy CPU-based approaches and up to 19x speed-ups over prior GPU-based approaches whilst learning superior Pareto front hypervolumes. We demonstrate MO-Playground's versatility by implementing a custom BRUCE humanoid robot environment and learning Pareto-optimal locomotion policies across 6 practical objectives in simulation, such as smoothness, efficiency and arm swinging. Our toolbox is available at https://dynamicmobility.github.io/moplayground/.
机构、总结、中文摘要均由AI分析而来，可能存在错误，请以论文正文为准。
