The paper shows that adding depth and segmentation prediction auxiliary tasks, supervised pre-training, and a complexity curriculum to A2C speeds up target-image navigation in realistic simulators.
Target-driven visual navigation in indoor scenes using deep reinforcement learning,
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
fields
cs.RO 1years
2019 1verdicts
CONDITIONAL 1representative citing papers
citing papers explorer
-
Vision-based Navigation Using Deep Reinforcement Learning
The paper shows that adding depth and segmentation prediction auxiliary tasks, supervised pre-training, and a complexity curriculum to A2C speeds up target-image navigation in realistic simulators.