机器人自主设定目标并学习技能，适应动态环境变化。
A Motivational Architecture for Open-Ended Learning Challenges in Robots
- 分层架构结合多种内在动机机制，实现目标自生成。
- 在真实机器人上验证，可持续学习新任务并适应环境变化。
- 适合研究长期自主学习与智能体自我驱动的科研人员。
构建能够自主与复杂动态环境交互的智能体，是人工智能系统在现实世界部署的关键前提。开放式学习框架揭示了此类智能体的核心挑战：自主生成新目标、获取达成目标所需技能（或技能课程），以及适应非平稳环境。尽管现有研究多聚焦于单一问题，但鲜有整合解决方案同时应对多项挑战。本文提出 H-GRAIL——一种分层架构，通过不同类型的内在动机与相互连接的学习机制，实现目标自主发现、技能学习、任务依赖的技能序列生成，并适应非平稳环境。我们在真实机器人场景中测试了 H-GRAIL，验证了其对开放式学习诸多挑战的有效应对能力。
原文摘要 · Abstract (English)
Developing agents capable of autonomously interacting with complex and dynamic environments, where task structures may change over time and prior knowledge cannot be relied upon, is a key prerequisite for deploying artificial systems in real-world settings. The open-ended learning framework identifies the core challenges for creating such agents, including the ability to autonomously generate new goals, acquire the necessary skills (or curricula of skills) to achieve them, and adapt to non-stationary environments. While many existing works tackles various aspects of these challenges in isolation, few propose integrated solutions that address them simultaneously. In this paper, we introduce H-GRAIL, a hierarchical architecture that, through the use of different typologies of intrinsic motivations and interconnected learning mechanisms, autonomously discovers new goals, learns the required skills for their achievement, generates skill sequences for tackling interdependent tasks, and adapts to non-stationary environments. We tested H-GRAIL in a real robotic scenario, demonstrating how the proposed solutions effectively address the various challenges of open-ended learning.
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。