To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments
This addresses the problem of navigation agent design for virtual environments, providing insights for future development, though it is incremental as it compares existing methods.
The paper compared learning-based and classical methods for navigation in virtual environments, finding that classical agents outperformed state-of-the-art learning-based agents on MINOS and Stanford benchmarks, with learned agents showing inferior collision avoidance and memory management but better handling of ambiguity and noise.
In this paper we compare learning-based methods and classical methods for navigation in virtual environments. We construct classical navigation agents and demonstrate that they outperform state-of-the-art learning-based agents on two standard benchmarks: MINOS and Stanford Large-Scale 3D Indoor Spaces. We perform detailed analysis to study the strengths and weaknesses of learned agents and classical agents, as well as how characteristics of the virtual environment impact navigation performance. Our results show that learned agents have inferior collision avoidance and memory management, but are superior in handling ambiguity and noise. These results can inform future design of navigation agents.