HARBOR自动化机器人强化学习全流程，降低工程门槛。
HARBOR: A Harness Framework for Agentic Robot Reinforcement Learning
- 用专用智能体分阶段执行任务，通过标准化指令与知识复用
- 在6个基准16项任务中实现端到端自动化，性能不低于默认配置
- 适合希望减少人工调参的机器人研发团队使用
强化学习（RL）已成为机器人学习的重要范式，尤其在仿真到现实（sim-to-real）场景中表现突出，但其广泛应用仍受限于算法背后的工程流程。构建任务、设计奖励函数和调参需大量专家投入，导致RL工作流成本高且难扩展。我们提出HARBOR，一种面向智能体的框架，将机器人强化学习自动化视为一种“工具链工程”问题：给定仿真代码库和任务说明，它能自动完成从环境搭建到策略训练的全流程。HARBOR将高层目标分解为由专用智能体执行的有限阶段，利用标准化命令、持久化产物、可执行门控和可复用知识，并通过去中心化并行试验与跨运行经验学习实现迭代扩展。我们在6个基准共16项任务上评估了HARBOR，涵盖操作、运动与双臂灵巧控制。结果表明，HARBOR实现了仿真强化学习全流程自动化，能自主设计奖励函数、优化算法参数以达到或超越默认配置，显著降低工程成本，且在实际令牌与运行时间开销下可行；生成的策略还可成功迁移到真实机器人上。
原文摘要 · Abstract (English)
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.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。