Emergence of Goal-Directed Behaviors via Active Inference with Self-Prior
Fuente:
arXiv
Enregistré dans:
| Auteurs principaux: | , , , |
|---|---|
| Format: | Preprint |
| Publié: |
2025
|
| Sujets: | |
| Accès en ligne: | |
| Tags: |
Ajouter un tag
Pas de tags, Soyez le premier à ajouter un tag!
|
| _version_ | 1866909897203908608 |
|---|---|
| author | Kim, Dongmin Kanazawa, Hoshinori Yoshida, Naoto Kuniyoshi, Yasuo |
| author_facet | Kim, Dongmin Kanazawa, Hoshinori Yoshida, Naoto Kuniyoshi, Yasuo |
| contents | Infants often exhibit goal-directed behaviors, such as reaching for a sensory stimulus, even when no external reward criterion is provided. These intrinsically motivated behaviors facilitate spontaneous exploration and learning of the body and environment during early developmental stages. Although computational modeling can offer insight into the mechanisms underlying such behaviors, many existing studies on intrinsic motivation focus primarily on how exploration contributes to acquiring external rewards. In this paper, we propose a novel density model for an agent's own multimodal sensory experiences, called the "self-prior," and investigate whether it can autonomously induce goal-directed behavior. Integrated within an active inference framework based on the free energy principle, the self-prior generates behavioral references purely from an intrinsic process that minimizes mismatches between average past sensory experiences and current observations. This mechanism is also analogous to the acquisition and utilization of a body schema through continuous interaction with the environment. We examine this approach in a simulated environment and confirm that the agent spontaneously reaches toward a tactile stimulus. Our study implements intrinsically motivated behavior shaped by the agent's own sensory experiences, demonstrating the spontaneous emergence of intentional behavior during early development. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2504_11075 |
| institution | arXiv |
| publishDate | 2025 |
| record_format | arxiv |
| spellingShingle | Emergence of Goal-Directed Behaviors via Active Inference with Self-Prior Kim, Dongmin Kanazawa, Hoshinori Yoshida, Naoto Kuniyoshi, Yasuo Artificial Intelligence 68T05, 68T40, 68T42 I.2.0; I.2.6; I.2.9 Infants often exhibit goal-directed behaviors, such as reaching for a sensory stimulus, even when no external reward criterion is provided. These intrinsically motivated behaviors facilitate spontaneous exploration and learning of the body and environment during early developmental stages. Although computational modeling can offer insight into the mechanisms underlying such behaviors, many existing studies on intrinsic motivation focus primarily on how exploration contributes to acquiring external rewards. In this paper, we propose a novel density model for an agent's own multimodal sensory experiences, called the "self-prior," and investigate whether it can autonomously induce goal-directed behavior. Integrated within an active inference framework based on the free energy principle, the self-prior generates behavioral references purely from an intrinsic process that minimizes mismatches between average past sensory experiences and current observations. This mechanism is also analogous to the acquisition and utilization of a body schema through continuous interaction with the environment. We examine this approach in a simulated environment and confirm that the agent spontaneously reaches toward a tactile stimulus. Our study implements intrinsically motivated behavior shaped by the agent's own sensory experiences, demonstrating the spontaneous emergence of intentional behavior during early development. |
| title | Emergence of Goal-Directed Behaviors via Active Inference with Self-Prior |
| topic | Artificial Intelligence 68T05, 68T40, 68T42 I.2.0; I.2.6; I.2.9 |
| url | https://arxiv.org/abs/2504.11075 |