Recent advancements in AI and deep learning have created a growing demand for artificial agents capable of performing tasks within increasingly complex environments. To address the challenges associated with continuous learning constraints and knowledge capacity in this context, cognitive architectures inspired by human cognition have gained significance. This study contributes to existing research by introducing a cognitive-attentional system employing a constructive neural network-based learning approach for continuous acquisition of procedural knowledge. We replace an incremental tabular Reinforcement Learning algorithm with a constructive neural network deep reinforcement learning mechanism for continuous sensorimotor knowledge acquisition, thereby enhancing the overall learning capacity. The primary emphasis of this modification centers on optimizing memory utilization and reducing training time. Our study presents a learning strategy that amalgamates deep reinforcement learning with procedural learning, mirroring the incremental learning process observed in human sensorimotor development. This approach is embedded within the CONAIM cognitive-attentional architecture, leveraging the cognitive tools of CST. The proposed learning mechanism allows the model to dynamically create and modify elements in its procedural memory, facilitating the reuse of previously acquired functions and procedures. Additionally, it equips the model with the capability to combine learned elements to effectively adapt to complex scenarios. A constructive neural network was employed, initiating with an initial hidden layer comprising one neuron. However, it possesses the capacity to adapt its internal architecture in response to its performance in procedural and sensorimotor learning tasks, inserting new hidden layers or neurons. Experimentation conducted through simulations involving a humanoid robot demonstrates the successful resolution of tasks that were previously unsolved through incremental knowledge acquisition. Throughout the training phase, the constructive agent achieved a minimum of 40% greater rewards and executed 8% more actions when compared to other agents. In the subsequent testing phase, the constructive agent exhibited a 15% increase in the number of actions performed in contrast to its counterparts.

人工智能和深度学习的最新进展对能够在日益复杂的环境中执行任务的人工智能体产生了日益增长的需求。为了解决这种背景下与持续学习限制和知识能力相关的挑战，受人类认知启发的认知架构变得意义重大。这项研究通过引入认知注意系统，采用基于构造性神经网络的学习方法来持续获取程序知识，为现有研究做出了贡献。我们用构造性神经网络深度强化学习机制取代增量表格强化学习算法，以连续获取感觉运动知识，从而提高整体学习能力。此修改的主要重点是优化内存利用率和减少训练时间。我们的研究提出了一种将深度强化学习与程序学习相结合的学习策略，反映了在人类感觉运动发展中观察到的增量学习过程。该方法嵌入 CONAIM 认知注意力架构中，利用 CST 的认知工具。所提出的学习机制允许模型动态创建和修改其程序存储器中的元素，从而促进先前获取的函数和程序的重用。此外，它还使模型能够结合学习到的元素，以有效适应复杂的场景。采用了一种构造性神经网络，以包含一个神经元的初始隐藏层开始。然而，它具有调整其内部架构的能力，以响应其在程序和感觉运动学习任务中的表现，插入新的隐藏层或神经元。通过涉及人形机器人的模拟进行的实验表明，可以成功解决以前通过增量知识获取无法解决的任务。在整个训练阶段，与其他智能体相比，建设性智能体获得了至少 40% 的奖励，执行的操作多了 8%。在随后的测试阶段，与同类代理相比，建设性代理执行的操作数量增加了 15%。