ARLO: A Framework for Automated Reinforcement Learning
This work addresses the problem of reducing the complexity and human effort required to apply RL techniques, making it more accessible for practitioners, though it is incremental as it builds on existing AutoRL research.
The authors tackled the challenge of making Reinforcement Learning (RL) more accessible by proposing ARLO, a framework for Automated Reinforcement Learning (AutoRL) that automates tasks like algorithm selection and hyper-parameter tuning, showing competitive performance on MuJoCo environments and a realistic dam environment with limited human intervention.
Automated Reinforcement Learning (AutoRL) is a relatively new area of research that is gaining increasing attention. The objective of AutoRL consists in easing the employment of Reinforcement Learning (RL) techniques for the broader public by alleviating some of its main challenges, including data collection, algorithm selection, and hyper-parameter tuning. In this work, we propose a general and flexible framework, namely ARLO: Automated Reinforcement Learning Optimizer, to construct automated pipelines for AutoRL. Based on this, we propose a pipeline for offline and one for online RL, discussing the components, interaction, and highlighting the difference between the two settings. Furthermore, we provide a Python implementation of such pipelines, released as an open-source library. Our implementation has been tested on an illustrative LQG domain and on classic MuJoCo environments, showing the ability to reach competitive performances requiring limited human intervention. We also showcase the full pipeline on a realistic dam environment, automatically performing the feature selection and the model generation tasks.