Ensemble and Auxiliary Tasks for Data-Efficient Deep Reinforcement Learning
This work addresses data efficiency in deep reinforcement learning, which is a challenge for applications with limited training data, but it is incremental as it builds on known methods without introducing a new paradigm.
The paper studied how combining ensemble methods and auxiliary tasks affects deep Q-learning performance under limited data constraints, specifically on ATARI games, and derived a bias-variance-covariance decomposition to analyze these interactions.
Ensemble and auxiliary tasks are both well known to improve the performance of machine learning models when data is limited. However, the interaction between these two methods is not well studied, particularly in the context of deep reinforcement learning. In this paper, we study the effects of ensemble and auxiliary tasks when combined with the deep Q-learning algorithm. We perform a case study on ATARI games under limited data constraint. Moreover, we derive a refined bias-variance-covariance decomposition to analyze the different ways of learning ensembles and using auxiliary tasks, and use the analysis to help provide some understanding of the case study. Our code is open source and available at https://github.com/NUS-LID/RENAULT.