Balancing Depth for Robustness: A Study on Reincarnating Reinforcement Learning Models

Balancing Depth for Robustness: A Study on Reincarnating Reinforcement Learning Models

This paper investigates the impact of adaptive network depth selection on the robustness and performance of Regenerative Reinforcement Learning (RRL) models. RRL accelerates learning by reusing previously computed results. We propose a task-driven approach to dynamically configure network depth to e...

Full description

Saved in:
Bibliographic Details
Main Authors: Gang Li, Zhuxiao Wang, Shaowei He, Xiyuan Chen, Yunlei Xie, Jiajun Hu, Kehe Wu, Jingping Jia
Format: Article
Language:English
Published: MDPI AG 2025-03-01
Series:Applied Sciences
Subjects:
reincarnating reinforcement learning
network depth
robustness
generalization ability
Online Access:https://www.mdpi.com/2076-3417/15/7/3830
Tags: Add Tag
No Tags, Be the first to tag this record!

Internet

https://www.mdpi.com/2076-3417/15/7/3830

Similar Items