The integration of reasoning, learning, and decision-making is key to build more general AI systems. As a step in this direction, we propose a novel neural-logic architecture that can solve both inductive logic programming (ILP) and deep reinforcement learning (RL) problems. Our architecture defines a restricted but expressive continuous space of first-order logic programs by assigning weights to predicates instead of rules. Therefore, it is fully differentiable and can be efficiently trained with gradient descent. Besides, in the deep RL setting with actor-critic algorithms, we propose a novel efficient critic architecture. Compared to state-of-the-art methods on both ILP and RL problems, our proposition achieves excellent performance, while being able to provide a fully interpretable solution and scaling much better, especially during the testing phase.

中文翻译：

---

可微逻辑机器

推理，学习和决策制定的集成对于构建更通用的AI系统至关重要。作为朝这个方向迈出的一步，我们提出了一种新颖的神经逻辑体系结构，可以解决归纳逻辑编程（ILP）和深度强化学习（RL）问题。我们的体系结构通过将权重分配给谓词而不是规则来定义一阶逻辑程序的受限但可表示的连续空间。因此，它是完全可微的，可以通过梯度下降有效地训练。此外，在具有演员评论算法的深度RL设置中，我们提出了一种新颖的高效评论者体系结构。与针对ILP和RL问题的最新方法相比，我们的主张具有出色的性能，同时能够提供完全可解释的解决方案，并且扩展性更好，