肌腱驱动手部灵巧协调的关节空间赋能策略发布
原标题：jamesheald/joint-space-empowerment
AI 摘要
Hugging Face 上发布了名为“Joint-Space Empowerment for Dexterous Coordination in Tendon-Driven Hands”的模型仓库，包含用于肌腱驱动手部灵巧协调的强化学习训练策略。该研究由 James Heald 等人完成，被 ICML 2026 接收为 Spotlight 论文。仓库提供了 Adroit 和 MyoHand 两种手部环境下的多个任务（如 BaodingBalls、DieReorient 等）的预训练模型和配置，并支持通过 JoSE 仓库的脚本加载和评估。
正文节选
--- license: mit library_name: stable-baselines3 tags: - reinforcement-learning - robotics - myosuite - gymnasium --- # Joint-Space Empowerment for Dexterous Coordination in Tendon-Driven Hands This repository contains the official trained policies for > **Joint-Space Empowerment for Dexterous Coordination in Tendon-Driven Hands** > *James Heald, Vittorio Caggiano, Vikash Kumar, Maneesh Sahani* > **ICML 2026 (Spotlight)** > 📜 [Paper](https://openreview.net/pdf?id=qI2eHwfNfh) | 💻 [Code](