Can I read Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison on EtoBox?

Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison by Lange, Moritz; Krystiniak, Noah; Engelhardt, Raphael C.; Konen, Wolfgang; Wiskott, Laurenz is a scholarly article available to read on EtoBox.

What is Improving Reinforcement Learning Efficiency with Auxiliary Tasks in Non-Visual Environments: A Comparison about?

Real-world reinforcement learning (RL) environments, whether in robotics or industrial settings, often involve non-visual observations and require not only efficient but also reliable and thus interpretable and flexible RL approaches. To improve efficiency, agents that perform state representation learning with auxiliary tasks have been widely studied in visual observation contexts. However, for real-world problems, dedicated representation learning modules that are decoupled from RL agents are more suited to meet requirements. This study compares common auxiliary tasks based on, to the best of our knowledge, the only decoupled representation learning method for low-dimensional non-visual observations. We evaluate potential improvements in sample efficiency and returns for environments ranging from a simple pendulum to a complex simulated robotics task. Our findings show that representation learning with auxiliary tasks only provides performance gains in sufficiently complex environments and that learning environment dynamics is preferable to predicting rewards. These insights can inform future development of interpretable representation learning approaches for non-visual observati

Author

Lange, Moritz; Krystiniak, Noah; Engelhardt, Raphael C.; Konen, Wolfgang; Wiskott, Laurenz

Published

2023

Language

EN