Attention has become a common ingredient in deep learning architectures. It adds a dynamical selection of information on top of the static selection of information supported by weights. In the same way, we can imagine a higher-order informational filter built on top of attention: an Attention Schema (AS), namely, a descriptive and predictive model of attention. In cognitive neuroscience, Attention Schema Theory (AST) supports this idea of distinguishing attention from AS. A strong prediction of this theory is that an agent can use its own AS to also infer the states of other agents' attention and consequently enhance coordination with other agents. As such, multi-agent reinforcement learning would be an ideal setting to experimentally test the validity of AST. We explore different ways in which attention and AS interact with each other. Our preliminary results indicate that agents that implement the AS as a recurrent internal control achieve the best performance. In general, these exploratory experiments suggest that equipping artificial agents with a model of attention can enhance their social intelligence.

翻译：注意已成为深度学习架构中的常见元素。它在权重支持的静态信息选择之上，增加了动态信息选择。同样，我们可以想象一种构建在注意之上的高阶信息过滤器：注意模式（AS），即对注意的描述性和预测性模型。在认知神经科学中，注意模式理论（AST）支持区分注意与AS这一观点。该理论的一个有力预测是，主体可以利用自身的AS来推断其他主体的注意状态，从而增强与其他主体的协调能力。因此，多主体强化学习将是实验验证AST有效性的理想场景。我们探索了注意与AS相互作用的多种方式。初步结果表明，将AS实现为循环内部控制的主体取得了最佳性能。总体而言，这些探索性实验表明，为人工主体配备注意模型可以增强其社会智能。