Object-Centric Representation Learning in Embodied Reinforcement Learning

与当代的深度强化学习系统相比，理解对象及其属性、动力学和交互作用的代理可以学习更强大和更具一般性的表示。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合成(通过归纳偏见或可微组合)形成了我们研究的主要焦点。研究领域：人工智能技术

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