Self-Emotion-Mediated Exploration in Artificial Intelligence Mirrors: Findings from Cognitive Psychology

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Assunção, Gustavo, Castelo-Branco, Miguel, Menezes, Paulo
Natura: Preprint
Pubblicazione: 2023
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866912577108312064
author Assunção, Gustavo
Castelo-Branco, Miguel
Menezes, Paulo
author_facet Assunção, Gustavo
Castelo-Branco, Miguel
Menezes, Paulo
contents 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.
format Preprint
id arxiv_https___arxiv_org_abs_2302_06615
institution arXiv
publishDate 2023
record_format arxiv
spellingShingle Self-Emotion-Mediated Exploration in Artificial Intelligence Mirrors: Findings from Cognitive Psychology
Assunção, Gustavo
Castelo-Branco, Miguel
Menezes, Paulo
Artificial Intelligence
Machine Learning
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.
title Self-Emotion-Mediated Exploration in Artificial Intelligence Mirrors: Findings from Cognitive Psychology
topic Artificial Intelligence
Machine Learning
url https://arxiv.org/abs/2302.06615