FM-EAC: Feature Model-based Enhanced Actor-Critic for Multi-Task Control in Dynamic Environments
This work addresses the challenge of multi-task control in dynamic environments for applications like urban and agricultural settings, but it appears incremental as it builds on existing MBRL and MFRL methods.
The paper tackles the problem of limited transferability in reinforcement learning across tasks and scenarios by proposing FM-EAC, a generalized algorithm that integrates planning, acting, and learning for multi-task control in dynamic environments, and it demonstrates consistent outperformance over state-of-the-art methods in simulations.
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.