Object-Centric Representation Learning in Embodied Reinforcement Learning

具身强化学习中以对象为中心的表示学习

• 批准号: 2486739
• 金额: --
• 依托单位: Imperial College London
• 依托单位国家: 英国
• 项目类别: Studentship
• 财政年份: 2020
• 资助国家: 英国
• 起止时间: 2020 至 无数据
• 项目状态: 已结题
• 来源: https://gtr.ukri.org/projects?ref=studentship-2486739
• 关键词: Object; Centric; Representation; Learning; Embodied

Agents which understand their environment in terms of objects, and their properties, dynamics and interactions, may learn more powerful and generalisable representations than contemporary Deep Reinforcement Learning systems. This ontological commitment underpins the formal logic utilised in Logic-based AI methods; whose synthesis (either through inductive bias or differentiable combination) with modern Deep Learning systems forms the primary focus of our investigation.Research area: Artificial intelligence technologies

从对象及其属性、动态和交互的角度理解其环境的智能体，可以学习比当代深度强化学习系统更强大和更通用的表示。这种本体论的承诺支撑了基于逻辑的人工智能方法中使用的形式逻辑;其与现代深度学习系统的合成（通过归纳偏差或可微组合）形成了我们研究的主要焦点。研究领域：人工智能技术