FM-EAC: Feature Model-based Enhanced Actor-Critic for Multi-Task Control in Dynamic Environments
Abstract
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.
Cite
@article{arxiv.2512.15430,
title = {FM-EAC: Feature Model-based Enhanced Actor-Critic for Multi-Task Control in Dynamic Environments},
author = {Quanxi Zhou and Wencan Mao and Manabu Tsukada and John C. S. Lui and Yusheng Ji},
journal= {arXiv preprint arXiv:2512.15430},
year = {2025}
}