Self-Emotion-Mediated Exploration in Artificial Intelligence Mirrors: Findings from Cognitive Psychology
This work addresses the problem of limited adaptability in AI models for researchers, offering an incremental approach to enhance autonomous learning through emotional mechanisms.
The paper tackled the lack of autonomous exploration in AI agents by proposing a bio-inspired reinforcement learning framework that uses epistemic and achievement emotions like surprise and pride to drive exploration, resulting in a 15.4% mean increase in surprise and correlations mirroring human behavior.
Background: Exploration of the physical environment is an indispensable precursor to information acquisition and knowledge consolidation for living organisms. Yet, current artificial intelligence models lack these autonomy capabilities during training, hindering their adaptability. This work proposes a learning framework for artificial agents to obtain an intrinsic exploratory drive, based on epistemic and achievement emotions triggered during data observation. Methods: This study proposes a dual-module reinforcement framework, where data analysis scores dictate pride or surprise, in accordance with psychological studies on humans. A correlation between these states and exploration is then optimized for agents to meet their learning goals. Results: Causal relationships between states and exploration are demonstrated by the majority of agents. A 15.4\% mean increase is noted for surprise, with a 2.8\% mean decrease for pride. Resulting correlations of $ρ_{surprise}=0.461$ and $ρ_{pride}=-0.237$ are obtained, mirroring previously reported human behavior. Conclusions: These findings lead to the conclusion that bio-inspiration for AI development can be of great use. This can incur benefits typically found in living beings, such as autonomy. Further, it empirically shows how AI methodologies can corroborate human behavioral findings, showcasing major interdisciplinary importance. Ramifications are discussed.