Search Results for author:
Found 8 papers, 6 papers with code
Habitat 3.0: A Co-Habitat for Humans, Avatars and Robots
We present Habitat 3. 0: a simulation platform for studying collaborative human-robot tasks in home environments.
What do we learn from a large-scale study of pre-trained visual representations in sim and real environments?
We present a large empirical investigation on the use of pre-trained visual representations (PVRs) for training downstream policies that execute real-world tasks.
Galactic: Scaling End-to-End Reinforcement Learning for Rearrangement at 100k Steps-Per-Second
Specifically, a Fetch robot (equipped with a mobile base, 7DoF arm, RGBD camera, egomotion, and onboard sensing) is spawned in a home environment and asked to rearrange objects - by navigating to an object, picking it up, navigating to a target location, and then placing the object at the target location.
Where are we in the search for an Artificial Visual Cortex for Embodied Intelligence?
Contrary to inferences from prior work, we find that scaling dataset size and diversity does not improve performance universally (but does so on average).
Offline Visual Representation Learning for Embodied Navigation
In this paper, we show that an alternative 2-stage strategy is far more effective: (1) offline pretraining of visual representations with self-supervised learning (SSL) using large-scale pre-rendered images of indoor environments (Omnidata), and (2) online finetuning of visuomotor representations on specific tasks with image augmentations under long learning schedules.
On the Use and Misuse of Absorbing States in Multi-agent Reinforcement Learning
In this work, we first demonstrate that sample complexity increases with the quantity of absorbing states in a toy supervised learning task for a fully connected network, while attention is more robust to variable size input.
Multi-agent Reinforcement Learning
reinforcement-learning
+1
Obstacle Tower: A Generalization Challenge in Vision, Control, and Planning
Unlike other benchmarks such as the Arcade Learning Environment, evaluation of agent performance in Obstacle Tower is based on an agent's ability to perform well on unseen instances of the environment.
Unity: A General Platform for Intelligent Agents
Recent advances in artificial intelligence have been driven by the presence of increasingly realistic and complex simulated environments.
