AI Article Synopsis
- The text explores the behaviors of organisms, questioning whether these actions serve a purpose or represent mere reactions, proposing that this distinction is overly simplistic.
- The authors advocate for a combined approach using two frameworks: multiscale competencies and goal-directedness in biology (TAME) and reinforcement learning (RL), to better understand both biological organisms and artificial agents.
- By integrating RL and TAME, the authors aim to generate new research questions that can enhance our understanding of biological behaviors and contribute to advancements in artificial intelligence development.
Article Abstract
Organisms play, explore, and mimic those around them. Is there a purpose to this behavior? Are organisms just behaving, or are they trying to achieve goals? We believe this is a false dichotomy. To that end, to understand organisms, we attempt to unify two approaches for understanding complex agents, whether evolved or engineered. We argue that formalisms describing multiscale competencies and goal-directedness in biology (e.g., TAME), and reinforcement learning (RL), can be combined in a symbiotic framework. While RL has been largely focused on higher-level organisms and robots of high complexity, TAME is naturally capable of describing lower-level organisms and minimal agents as well. We propose several novel questions that come from using RL/TAME to understand biology as well as ones that come from using biology to formulate new theory in AI. We hope that the research programs proposed in this piece shape future efforts to understand biological organisms and also future efforts to build artificial agents.
Download full-text PDF |
Source |
|---|---|
| http://dx.doi.org/10.1016/j.biosystems.2023.105107 | DOI Listing |
Publication Analysis
Top Keywords
Similar Publications
Episodic retrieval for model-based evaluation in sequential decision tasks.
Psychol Rev
January 2025
Department of Cognitive Science, University of California, San Diego.
It has long been hypothesized that episodic memory supports adaptive decision making by enabling mental simulation of future events. Yet, attempts to characterize this process are surprisingly rare. On one hand, memory research is often carried out in settings that are far removed from ecological contexts of decision making.
View Article and Find Full Text PDFA safe-enhanced fully closed-loop artificial pancreas controller based on deep reinforcement learning.
PLoS One
January 2025
Institute of Visual Informatics, The National University of Malaysia (UKM), Bangi, Malaysia.
Patients with type 1 diabetes and their physicians have long desired a fully closed-loop artificial pancreas (AP) system that can alleviate the burden of blood glucose regulation. Although deep reinforcement learning (DRL) methods theoretically enable adaptive insulin dosing control, they face numerous challenges, including safety and training efficiency, which have hindered their clinical application. This paper proposes a safe and efficient adaptive insulin delivery controller based on DRL.
View Article and Find Full Text PDFUnlabelled: Autism Spectrum Disorder (ASD) is characterized by restricted and repetitive behaviors and social differences, both of which may manifest, in part, from underlying differences in corticostriatal circuits and reinforcement learning. Here, we investigated reinforcement learning in mice with mutations in either or , both high-confidence ASD risk genes associated with major syndromic forms of ASD. Using an odor-based two-alternative forced choice (2AFC) task, we tested adolescent mice of both sexes and found male and heterozygote (Het) mice showed enhanced learning performance compared to their wild type (WT) siblings.
View Article and Find Full Text PDFOpioid reward and deep brain stimulation of the lateral hypothalamic area.
Vitam Horm
January 2025
Department of Physiology, School of Medicine, Tehran University of Medical Sciences, Tehran, Iran. Electronic address:
Opioid use disorder (OUD) is considered a global health issue that affects various aspects of patients' lives and poses a considerable burden on society. Due to the high prevalence of remissions and relapses, novel therapeutic approaches are required to manage OUD. Deep brain stimulation (DBS) is one of the most promising clinical breakthroughs in translational neuroscience.
View Article and Find Full Text PDFExplainable vision transformer for automatic visual sleep staging on multimodal PSG signals.
NPJ Digit Med
January 2025
Graduate School of Data Science, Seoul National University, Seoul, Republic of Korea.
Polysomnography (PSG) is crucial for diagnosing sleep disorders, but manual scoring of PSG is time-consuming and subjective, leading to high variability. While machine-learning models have improved PSG scoring, their clinical use is hindered by the 'black-box' nature. In this study, we present SleepXViT, an automatic sleep staging system using Vision Transformer (ViT) that provides intuitive, consistent explanations by mimicking human 'visual scoring'.
View Article and Find Full Text PDFWant AI Summaries of new PubMed Abstracts delivered to your In-box?
Enter search terms and have AI summaries delivered each week - change queries or unsubscribe any time!