44 citations · 243 across the 24 of their papers we have counts for
4 papers · 1 filter
MultiON: Benchmarking Semantic Map Memory using Multi-Object Navigation
Saim Wani, Shivansh Patel, Unnat Jain +2
Navigation tasks in photorealistic 3D environments are challenging because they require perception and effective planning under partial observability. Recent work shows that map-li…
AllenAct: A Framework for Embodied AI Research
Luca Weihs, Jordi Salvador, Klemen Kotar +4
The domain of Embodied AI, in which agents learn to complete tasks through interaction with their environment from egocentric observations, has experienced substantial growth with…
A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks
Unnat Jain, Luca Weihs, Eric Kolve +4
Autonomous agents must learn to collaborate. It is not scalable to develop a new centralized agent every time a task's difficulty outpaces a single agent's abilities. While multi-a…
Bridging the Imitation Gap by Adaptive Insubordination
Luca Weihs, Unnat Jain, Iou-Jen Liu +4
In practice, imitation learning is preferred over pure reinforcement learning whenever it is possible to design a teaching agent to provide expert supervision. However, we show tha…