PvP：基于本体感知-特权对比表征的数据高效人形机器人学习
PvP: Data-Efficient Humanoid Robot Learning with Proprioceptive-Privileged Contrastive Representations
把本体感知状态与特权状态做对比学习来学紧凑潜变量表征，可直接迁移到视觉-本体多模态的具身策略学习中，用来缓解部分可观测下的样本低效；其 SRL4Humanoid 框架也为表征学习与 RL 结合的消融提供了可复用基线。
原文依据 PvP learns compact and task-relevant latent representations without requiring hand-crafted data augmentations
摘要译文
由模型翻译 · 术语统一 · 请对照原文核对关键结论实现高效且鲁棒的全身控制（WBC）是人形机器人在动态环境中执行复杂任务的关键。尽管强化学习（RL）在该领域已取得成功，但由于人形机器人动力学的复杂性与部分可观测性，其样本效率低仍是显著挑战。为解决这一局限，我们提出 PvP，一个本体感知-特权对比学习框架，利用本体感知状态与特权状态之间的内在互补性。PvP 无需手工设计的数据增强即可学习紧凑且与任务相关的潜变量表征，从而实现更快、更稳定的策略学习。为支持系统性评测，我们构建了 SRL4Humanoid，这是首个统一且模块化的框架，为人形机器人学习提供代表性状态表征学习（SRL）方法的高质量实现。在 LimX Oli 机器人上针对速度跟踪与运动模仿任务的大量实验表明，与基线 SRL 方法相比，PvP 显著提升了样本效率与最终性能。我们的研究进一步给出了将 SRL 与 RL 结合用于人形机器人全身控制的实践性洞见，为数据高效的人形机器人学习提供了有价值的指导。
英文原文摘要 1327 字符
Achieving efficient and robust whole-body control (WBC) is essential for enabling humanoid robots to perform complex tasks in dynamic environments. Despite the success of reinforcement learning (RL) in this domain, its sample inefficiency remains a significant challenge due to the intricate dynamics and partial observability of humanoid robots. To address this limitation, we propose **PvP**, a **P**roprioceptive-**P**rivileged contrastive learning framework that leverages the intrinsic complementarity between proprioceptive and privileged states. PvP learns compact and task-relevant latent representations without requiring hand-crafted data augmentations, enabling faster and more stable policy learning. To support systematic evaluation, we develop **SRL4Humanoid**, the first unified and modular framework that provides high-quality implementations of representative state representation learning (SRL) methods for humanoid robot learning. Extensive experiments on the LimX Oli robot across velocity tracking and motion imitation tasks demonstrate that PvP significantly improves sample efficiency and final performance compared to baseline SRL methods. Our study further provides practical insights into integrating SRL with RL for humanoid WBC, offering valuable guidance for data-efficient humanoid robot learning.