Saved in:
Bibliographic Details
Main Authors: Zhou, Quanxi, Mao, Wencan, Tsukada, Manabu, Lui, John C. S., Ji, Yusheng
Format: Preprint
Published: 2025
Subjects:
Online Access:https://arxiv.org/abs/2512.15430
Tags: Add Tag
No Tags, Be the first to tag this record!
_version_ 1866914205529014272
author Zhou, Quanxi
Mao, Wencan
Tsukada, Manabu
Lui, John C. S.
Ji, Yusheng
author_facet Zhou, Quanxi
Mao, Wencan
Tsukada, Manabu
Lui, John C. S.
Ji, Yusheng
contents Model-based reinforcement learning (MBRL) and model-free reinforcement learning (MFRL) evolve along distinct paths but converge in the design of Dyna-Q [1]. However, modern RL methods still struggle with effective transferability across tasks and scenarios. Motivated by this limitation, we propose a generalized algorithm, Feature Model-Based Enhanced Actor-Critic (FM-EAC), that integrates planning, acting, and learning for multi-task control in dynamic environments. FM-EAC combines the strengths of MBRL and MFRL and improves generalizability through the use of novel feature-based models and an enhanced actor-critic framework. Simulations in both urban and agricultural applications demonstrate that FM-EAC consistently outperforms many state-of-the-art MBRL and MFRL methods. More importantly, different sub-networks can be customized within FM-EAC according to user-specific requirements.
format Preprint
id arxiv_https___arxiv_org_abs_2512_15430
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle FM-EAC: Feature Model-based Enhanced Actor-Critic for Multi-Task Control in Dynamic Environments
Zhou, Quanxi
Mao, Wencan
Tsukada, Manabu
Lui, John C. S.
Ji, Yusheng
Machine Learning
Artificial Intelligence
Model-based reinforcement learning (MBRL) and model-free reinforcement learning (MFRL) evolve along distinct paths but converge in the design of Dyna-Q [1]. However, modern RL methods still struggle with effective transferability across tasks and scenarios. Motivated by this limitation, we propose a generalized algorithm, Feature Model-Based Enhanced Actor-Critic (FM-EAC), that integrates planning, acting, and learning for multi-task control in dynamic environments. FM-EAC combines the strengths of MBRL and MFRL and improves generalizability through the use of novel feature-based models and an enhanced actor-critic framework. Simulations in both urban and agricultural applications demonstrate that FM-EAC consistently outperforms many state-of-the-art MBRL and MFRL methods. More importantly, different sub-networks can be customized within FM-EAC according to user-specific requirements.
title FM-EAC: Feature Model-based Enhanced Actor-Critic for Multi-Task Control in Dynamic Environments
topic Machine Learning
Artificial Intelligence
url https://arxiv.org/abs/2512.15430