To Learn or Not to Learn: Analyzing the Role of Learning for Navigation in Virtual Environments
arXiv:1907.11770
Abstract
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.
References in corpus (9)
- On Evaluation of Embodied Navigation Agents
- Matterport3D: Learning from RGB-D Data in Indoor Environments
- Sample Efficient Actor-Critic with Experience Replay
- MINOS: Multimodal Indoor Simulator for Navigation in Complex Environments
- Neural SLAM: Learning to Explore with External Memory
- Neural Map: Structured Memory for Deep Reinforcement Learning
- CHALET: Cornell House Agent Learning Environment
- Unifying Map and Landmark Based Representations for Visual Navigation
- Benchmarking Classic and Learned Navigation in Complex 3D Environments
Cited by in corpus (4)
- Learning hierarchical relationships for object-goal navigation
- SoundSpaces: Audio-Visual Navigation in 3D Environments
- Efficient Robotic Object Search via HIEM: Hierarchical Policy Learning with Intrinsic-Extrinsic Modeling
- Point Cloud Based Reinforcement Learning for Sim-to-Real and Partial Observability in Visual Navigation