A robot cognitive model learns which action to select

What is it about?

Cognition entails those mental processes enabling understanding the current situation through senses, experience, and thought, and supporting the acquisition of new knowledge. A fundamental contribution in cognition is offered by the working memory, that is a small, short-term memory containing and protecting from interference goal-relevant pieces of information. Grounding our work on biologicaland neuroscientific studies, we modeled and implemented working memory processes in a software model that can simultaneously act as short-term memory and actions generator, thanks to the use of a reinforcement-driven mechanism for chunk selection. We tested the model with robot relevant tasks to assess how the proposed solution can learn to solve a problem on the basis of a delayed reward.

Featured Image

Photo by Prokhor Minin on Unsplash

Photo by Prokhor Minin on Unsplash