The ability to automatically learn movements and behaviors of increasing complexity is a long-term goal in autonomous systems. Indeed, this is a very complex problem that involves understanding how knowledge is acquired and reused by humans as well as proposing mechanisms that allow artificial agents to reuse previous knowledge. Inspired by Jean Piaget's theory's first three sensorimotor substages, this work presents a cognitive agent based on CONAIM (Conscious Attention-Based Integrated Model) that can learn procedures incrementally. Throughout the paper, we show the cognitive functions required in each substage and how adding new functions helps address tasks previously unsolved by the agent. Experiments were conducted with a humanoid robot in a simulated environment modeled with the Cognitive Systems Toolkit (CST) performing an object tracking task. The system is modeled using a single procedural learning mechanism based on Reinforcement Learning. The increasing agent's cognitive complexity is managed by adding new terms to the reward function for each learning phase. Results show that this approach is capable of solving complex tasks incrementally.
翻译:自动地学习运动和行为并且愈加复杂是自主系统的一个长期目标。这是一个非常复杂的问题,既要理解人类是如何获取和重用知识的,也要提出机制,使得人工智能代理能够重用之前的知识。本文的灵感来自Jean Piaget的理论中的前三个感觉-运动阶段,提出了一种基于CONAIM(意识主导的关注集成模型)的认知代理,可以逐步学习程序。在整个论文中,我们展示了在每个阶段中所需的认知功能,以及如何通过添加新功能来帮助解决以前未被该代理解决的任务。实验是在一个用认知系统工具包(Cognitive Systems Toolkit)建模的模拟环境中进行的,由一个人形机器人执行对象跟踪任务。该系统使用基于强化学习的单一过程式学习机制进行建模。通过为每个学习阶段添加新术语,可以管理代理的认知复杂性增加。结果表明,这种方法能够逐步解决复杂的任务。