Object-Centric Representation Learning in Embodied Reinforcement Learning

智能体可以根据对象及其属性、动态和相互作用来理解它们所处的环境，可能会比当前的深度强化学习系统学习更强大、更通用的表征。这种本体论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综合（通过归纳偏差或可微分组合）形成了我们研究的主要焦点。研究方向：人工智能技术

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