Directly Attention loss adjusted prioritized experience replay

Abstract Prioritized Experience Replay enables the model to learn more about relatively important samples by artificially changing their accessed frequencies. However, this non-uniform sampling method shifts the state-action distribution that is originally used to estimate Q-value functions, which b...

Descripció completa

Dades bibliogràfiques

Autors principals:	Zhuoying Chen, Huiping Li, Zhaoxu Wang
Format:	Artigo
Idioma:	Inglês
Publicat:	Springer 2025-04-01
Col·lecció:	Complex & Intelligent Systems
Matèries:	Prioritized experience replay Parallel self-attention network Priority-encouragement mechanism Multi-USV
Accés en línia:	https://doi.org/10.1007/s40747-025-01852-6
Etiquetes:	Afegir etiqueta Sense etiquetes, Sigues el primer a etiquetar aquest registre!