Improved Training Mechanism for Reinforcement Learning via Online Model Selection
By: Aida Afshar, Aldo Pacchiano
Potential Business Impact:
Teaches computers to pick the best learning strategy.
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.
Similar Papers
Efficient Model-Based Reinforcement Learning for Robot Control via Online Learning
Robotics
Teaches robots to learn by doing, faster.
Efficient Adaptation of Reinforcement Learning Agents to Sudden Environmental Change
Machine Learning (CS)
Helps robots learn new tricks without forgetting old ones.
Efficient Hyperparameter Search for Non-Stationary Model Training
Machine Learning (CS)
Saves money training smart computer programs faster.