İçeriğe geç
akaturk Akademik ölçüm

Makale detayı · 2024 · article

Diffusion Policies for Out-of-Distribution Generalization in Offline Reinforcement Learning

YÖKSİS OpenAlex Üst %10
Yıl2024
Atıf16OpenAlex
Yüzdelik%93,2
FWCI3,581,00 = dünya ortalaması
Scopus (SJR)Q1
WoS (JCR)Q1

Veri kaynağı ayrımı

  • YÖKSİSYÖKSİS makale kaydı
  • YÖKSİS dergi adıIEEE Robotics and Automation Letters
  • Katalog eşleşmesi (ISSN)IEEE Robotics and Automation Letters
  • OpenAlexOpenAlex zenginleştirmesi (özet, atıf, konular)
  • Semantic Scholaratıf sayısı (OpenAlex ile birleştirilmez)

Özet

OpenAlex İngilizce

Offline Reinforcement Learning (RL) methods leverage previous experiences to learn better policies than the behavior policy used for data collection. However, they face challenges handling distribution shifts due to the lack of online interaction during training. To this end, we propose a novel method named State Reconstruction for Diffusion Policies (SRDP) that incorporates state reconstruction feature learning in the recent class of diffusion policies to address the problem of out-of-distribution (OOD) generalization. Our method promotes learning of generalizable state representation to alleviate the distribution shift caused by OOD states. To illustrate the OOD generalization and faster convergence of SRDP, we design a novel 2D Multimodal Contextual Bandit environment and realize it on a 6-DoF real-world UR10 robot, as well as in simulation, and compare its performance with prior algorithms. In particular, we show the importance of the proposed state reconstruction via ablation studies. In addition, we assess the performance of our model on standard continuous control benchmarks (D4RL), namely the navigation of an 8-DoF ant and forward locomotion of half-cheetah, hopper, and walker2d, achieving state-of-the-art results. Finally, we demonstrate that our method can achieve 167% improvement over the competing baseline on a sparse continuous control navigation task where various regions of the state space are removed from the offline RL dataset, including the region encapsulating the goal.

Konular

Atıflar

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

16atıfOpenAlex · cited_by_count (önbellek / veritabanı)

Yazarlar

3
  1. SUZAN ECE ADA 1
  2. ERHAN ÖZTOP ÖZYEĞİN ÜNİVERSİTESİ 2
  3. EMRE UĞUR ORTA DOĞU TEKNİK ÜNİVERSİTESİ 3