AI Agents 相关度: 9/10

Accelerating Robotic Reinforcement Learning with Agent Guidance

Haojun Chen, Zili Zou, Chengdong Ma, Yaoxiang Pu, Haotong Zhang, Yuanpei Chen, Yaodong Yang
arXiv: 2602.11978v1 发布: 2026-02-12 更新: 2026-02-12

AI 摘要

AGPS通过多模态智能体指导强化学习,提升机器人训练效率,降低对人工干预的依赖。

主要贡献

  • 提出Agent-guided Policy Search (AGPS)框架
  • 使用多模态智能体代替人工进行机器人学习指导
  • 在精确插入和柔性物体操作任务上验证了AGPS的有效性

方法论

AGPS利用智能体作为语义世界模型,提供纠正性路点和空间约束,指导机器人进行探索和策略优化。

原文摘要

Reinforcement Learning (RL) offers a powerful paradigm for autonomous robots to master generalist manipulation skills through trial-and-error. However, its real-world application is stifled by severe sample inefficiency. Recent Human-in-the-Loop (HIL) methods accelerate training by using human corrections, yet this approach faces a scalability barrier. Reliance on human supervisors imposes a 1:1 supervision ratio that limits fleet expansion, suffers from operator fatigue over extended sessions, and introduces high variance due to inconsistent human proficiency. We present Agent-guided Policy Search (AGPS), a framework that automates the training pipeline by replacing human supervisors with a multimodal agent. Our key insight is that the agent can be viewed as a semantic world model, injecting intrinsic value priors to structure physical exploration. By using executable tools, the agent provides precise guidance via corrective waypoints and spatial constraints for exploration pruning. We validate our approach on two tasks, ranging from precision insertion to deformable object manipulation. Results demonstrate that AGPS outperforms HIL methods in sample efficiency. This automates the supervision pipeline, unlocking the path to labor-free and scalable robot learning. Project website: https://agps-rl.github.io/agps.

标签

强化学习 机器人 智能体 自主学习 多模态

arXiv 分类

cs.RO cs.AI