Self-mediated exploration in artificial intelligence inspired by cognitive psychology. (arXiv:2302.06615v1 [cs.AI])

Exploration of the physical environment is an indispensable precursor to data
acquisition and enables knowledge generation via analytical or direct trialing.
Artificial Intelligence lacks the exploratory capabilities of even the most
underdeveloped organisms, hindering its autonomy and adaptability. Supported by
cognitive psychology, this works links human behavior and artificial agents to
endorse self-development. In accordance with reported data, paradigms of
epistemic and achievement emotion are embedded to machine-learning methodology
contingent on their impact when decision making. A study is subsequently
designed to mirror previous human trials, which artificial agents are made to
undergo repeatedly towards convergence. Results demonstrate causality, learned
by the vast majority of agents, between their internal states and exploration
to match those reported for human counterparts. The ramifications of these
findings are pondered for both research into human cognition and betterment of
artificial intelligence.