Constructivist procedural learning for grounded cognitive agents

Constructivism is a learning theory based on the idea that individuals actively build their understanding of the world through their interactions with their environment. Learning is a dynamic process where new knowledge builds on prior knowledge, and a learner's mental models are continually refined by their experiences. Building on this theoretical framework and Drescher's seminal contributions to constructivist AI, this paper explores constructivism within the context of LIDA (Learning Intelligent Decision Agent), a biologically inspired cognitive architecture. Specifically, I develop a modified version of Drescher's schema mechanism, which I use to implement LIDA's Procedural Memory and Action Selection modules. I demonstrate that an agent based on this implementation can construct an accurate internal model of its environmental interactions and use that model to select goal-directed behaviors. This work significantly advances LIDA's computational capabilities by implementing grounded instructionist procedural learning, hierarchical action plans, and the selection of exploratory behaviors. These computational enhancements will enable the creation of more sophisticated LIDA-based agents that can operate in more complex environments where the hand-coding of procedural knowledge is infeasible. An alternate way to view this work is as an enhancement to Drescher's schema mechanism, which is a purely symbolic and ungrounded cognitive system. LIDA's sensory and perceptual systems provide a means by which the schema mechanism's representations can be grounded. This, in itself, is an important contribution of this paper.