İçeriğe geç
akaturk Akademik ölçüm

Makale detayı · 2023 · article

Exploration With Intrinsic Motivation Using Object–Action–Outcome Latent Space

YÖKSİS OpenAlex Açık erişim · green
Yıl2023
Atıf2OpenAlex
Yüzdelik%56,5
FWCI0,141,00 = dünya ortalaması
Scopus (SJR)Q1
WoS (JCR)Q1

Veri kaynağı ayrımı

  • YÖKSİSYÖKSİS makale kaydı
  • YÖKSİS dergi adıIEEE Transactions on Cognitive and Developmental Systems
  • Katalog eşleşmesi (ISSN)IEEE Transactions on Cognitive and Developmental Systems
  • OpenAlexOpenAlex zenginleştirmesi (özet, atıf, konular)
  • Semantic Scholaratıf sayısı (OpenAlex ile birleştirilmez)

Özet

OpenAlex İngilizce

One effective approach for equipping artificial agents with sensorimotor skills is to use self-exploration. To do this efficiently is critical, as time and data collection are costly. In this study, we propose an exploration mechanism that blends action, object, and action outcome representations into a latent space, where local regions are formed to host forward model (FM) learning. The agent uses intrinsic motivation to select the FM with the highest learning progress (LP) to adopt at a given exploration step. This parallels how infants learn, as high LP indicates that the learning problem is neither too easy nor too difficult in the selected region. The proposed approach is validated with a simulated robot in a tabletop environment. The simulation scene comprises a robot and various objects, where the robot interacts with one of them each time using a set of parameterized actions and learns the outcomes of these interactions. With the proposed approach, the robot organizes its curriculum of learning as in existing intrinsic motivation approaches and outperforms them in learning speed. Moreover, the learning regime demonstrates features that partially match infant development; in particular, the proposed system learns to predict the outcomes of different skills in a staged manner.

Konular

Atıflar

OpenAlex cited_by_count. WoS veya Scopus atıf sayısı değildir; o kaynaklar için ayrı kolon yoktur.

2atıfOpenAlex · cited_by_count (önbellek / veritabanı)

Yerel katalogda bu makaleye atıf yapan 1 yayın (OpenAlex referans eşleşmesi; tam dünya listesi değildir).

  1. 2025 Interleaved Multitask Learning with Energy Modulated Learning ProgressAtıf 1 · OpenAlex

Yazarlar

4
  1. MELİSA İDİL ŞENER 1
  2. Yukie Nagai 2
  3. ERHAN ÖZTOP ÖZYEĞİN ÜNİVERSİTESİ 3
  4. EMRE UĞUR ORTA DOĞU TEKNİK ÜNİVERSİTESİ 4