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:
Online Access:https://www.mdpi.com/2076-3417/15/7/3830
Tags: Add Tag
No Tags, Be the first to tag this record!
Description
Summary: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 explore the best architecture on Atari 2600 games. The experimental results show that a seven-layer network achieves the best balance between feature extraction, policy learning, and robustness, achieving an IQM score of 1.2 in a pool of 10 games. While deeper networks risk overfitting, shallower architectures struggle to cope with complex task dynamics. Our results highlight the key role of adaptive depth in enhancing the generalization, stability, and efficiency of RRL models.
ISSN:2076-3417