Offline reinforcement learning combining generalized advantage estimation and modality decomposition interaction

Abstract Transformers show great potential in offline reinforcement learning via trajectory sequence modeling for action prediction. However, existing Transformer-based methods face limitations, such as ineffective trajectory stitching and the neglect of deep interactions within and between multimod...

Full description

Saved in:
Bibliographic Details
Main Authors: Kaixin Jin, Lifang Wang, Xiwen Wang, Wei Guo, Qiang Han, Xiaoqing Yu
Format: Article
Language:English
Published: Nature Portfolio 2025-05-01
Series:Scientific Reports
Subjects:
Online Access:https://doi.org/10.1038/s41598-025-98572-1
Tags: Add Tag
No Tags, Be the first to tag this record!