Improved Training Mechanism for Reinforcement Learning via Online Model Selection
This work addresses the challenge of efficient and stable training in reinforcement learning for practitioners, though it appears incremental by applying existing online selection techniques to RL contexts.
The paper tackles the problem of online model selection in reinforcement learning by integrating selection methods to adaptively choose the right agent configuration, resulting in improved efficiency and performance gains as supported by theoretical and empirical evidence.
We study the problem of online model selection in reinforcement learning, where the selector has access to a class of reinforcement learning agents and learns to adaptively select the agent with the right configuration. Our goal is to establish the improved efficiency and performance gains achieved by integrating online model selection methods into reinforcement learning training procedures. We examine the theoretical characterizations that are effective for identifying the right configuration in practice, and address three practical criteria from a theoretical perspective: 1) Efficient resource allocation, 2) Adaptation under non-stationary dynamics, and 3) Training stability across different seeds. Our theoretical results are accompanied by empirical evidence from various model selection tasks in reinforcement learning, including neural architecture selection, step-size selection, and self model selection.