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...

Full description

Saved in:
Bibliographic Details
Main Authors: Zhuoying Chen, Huiping Li, Zhaoxu Wang
Format: Article
Language:English
Published: Springer 2025-04-01
Series:Complex & Intelligent Systems
Subjects:
Online Access:https://doi.org/10.1007/s40747-025-01852-6
Tags: Add Tag
No Tags, Be the first to tag this record!