Memory-Augmented Reinforcement Learning for Image-Goal Navigation
Lina Mezghan,Sainbayar Sukhbaatar,Thibaut Lavril,Oleksandr Maksymets,Dhruv Batra,Piotr Bojanowski,Karteek Alahari,Lina Mezghan,Sainbayar Sukhbaatar,Thibaut Lavril,Oleksandr Maksymets,Dhruv Batra,Piotr Bojanowski,Karteek Alahari
In this work, we present a memory-augmented approach for image-goal navigation. Earlier attempts, including RL-based and SLAM-based approaches have either shown poor generalization performance, or are heavily-reliant on pose/depth sensors. Our method is based on an attention-based end-to-end model that leverages an episodic memory to learn to navigate. First, we train a state-embedding network in ...
