Image Augmentation-Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes
IEEE Transactions on Games · 2024-09 · 16 (3) · 509-517
DOI: 10.1109/tg.2023.3288042 ↗Kurz gefasst
Fachartikel in der Zeitschrift IEEE Transactions on Games, 2024-09. Verfasst von Zheng Fang und 2 weiteren Autor:innen. Die Arbeit wurde bisher 3-mal zitiert (Crossref). Gefördert von: Shaanxi Key Research and Development Program.
Abstract (Originalsprache)
Many real-life tasks can be abstracted as sparse reward visual scenes, which can make it difficult for an agent to accomplish tasks accepting only images and sparse reward. To address this problem, we split it into two parts: visual representation and sparse reward, and propose our novel framework, called image augmentation-based momentum memory intrinsic reward, which combines self-supervised representation learning with intrinsic motivation. For visual representation, we acquire a representation driven by a combination of image-augmented forward dynamics and reward. To handle sparse reward, we design a new type of intrinsic reward called momentum memory intrinsic reward, which uses the difference between the outputs from the current model (online network) and the historical model (target network) to indicate the agent's state familiarity. We evaluate our method on a visual navigation task with sparse reward in VizDoom and demonstrate that it achieves state-of-the-art performance in terms of sample efficiency. Our method is at least two times faster than existing methods and reaches a 100% success rate.
Förderung
- Shaanxi Key Research and Development Program
Zitieren
APA
Fang, Z., Zhao, B., & Liu, G. (2024). Image Augmentation-Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes. IEEE Transactions on Games, 16(3), 509-517. https://doi.org/10.1109/tg.2023.3288042
Vancouver
Fang Z, Zhao B, Liu G. Image Augmentation-Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes. IEEE Transactions on Games. 2024;16(3):509-517. doi:10.1109/tg.2023.3288042
BibTeX
@article{Fang2024,
author = {Fang, Zheng and Zhao, Biao and Liu, Guizhong},
title = {Image Augmentation-Based Momentum Memory Intrinsic Reward for Sparse Reward Visual Scenes},
journal = {IEEE Transactions on Games},
year = {2024},
volume = {16},
number = {3},
pages = {509--517},
doi = {10.1109/tg.2023.3288042}
}
EUVIMED