HARBOR：面向智能体机器人强化学习的框架
HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning
AI总结：
提出HARBOR框架，通过将机器人强化学习自动化视为框架工程问题，利用专用智能体、标准化命令和可复用知识，在模拟中自动完成从环境搭建到策略训练的全流程，并在6个基准测试和16个任务中验证其有效性。
摘要：
强化学习已成为机器人学习的一种强大范式，特别是在模拟到现实的环境中，但其更广泛的采用仍受限于围绕算法的工程流程。构建任务、设计奖励和调整超参数需要大量专家努力，使得强化学习工作流程成本高昂且难以扩展。我们提出HARBOR，一个智能体框架，将机器人强化学习自动化视为一个框架工程问题：给定一个模拟器代码库和一个任务规范，它自动完成从环境设置到模拟中策略训练的工作流程。HARBOR将此类高级目标分解为有界阶段，由专用智能体通过标准化命令、持久化工件、可执行门和可复用知识执行，并通过去中心化并行试验和跨运行经验学习来扩展迭代。我们在6个基准测试和总共16个任务上评估HARBOR，涵盖操作、移动和双臂灵巧控制。我们证明HARBOR端到端地自动化了模拟强化学习工作流程，设计奖励，调整算法以匹配或改进默认配置，并以实用的令牌和挂钟成本减少了工程工作量；生成的策略也可以转移到真实机器人。
英文摘要：
Reinforcement learning (RL) has become a powerful paradigm for robot learning, particularly in sim-to-real settings, but its broader adoption remains limited by the engineering pipeline surrounding the algorithms. Building tasks, shaping rewards, and tuning hyperparameters require substantial expert effort, making RL workflows costly and difficult to scale. We introduce HARBOR, an agentic framework that frames robot RL automation as a harness-engineering problem: given a simulator codebase and a task specification, it automates the workflow from environment setup to policy training in simulation. HARBOR decomposes such high-level objectives into bounded stages executed by specialized agents through standardized commands, persistent artifacts, executable gates, and reusable knowledge, and scales iteration via decentralized parallel trials and experience learning across runs. We evaluate HARBOR across 6 benchmarks and 16 tasks in total, spanning manipulation, locomotion, and bimanual dexterous control. We demonstrate that HARBOR automates the simulation RL workflow end-to-end, designs rewards, tunes algorithms to match or improve over default configurations, and reduces engineering effort at practical token and wall-clock cost; the resulting policies can also be transferred to real robots.
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。
