Alvaro Herrasti

We introduce RoboTHOR to democratize research in interactive and embodied visual AI. Expand

We present an approach for answering questions that span multiple sentences and exhibit sophisticated cross-sentence anaphoric phenomena, evaluating on a rich source of such questions – the math portion of the Scholastic Aptitude Test. Expand

We show that embodied adversarial reinforcement learning agents playing cache, a variant of hide-and-seek, in a high fidelity, interactive, environment, learn representations of their observations encoding information such as occlusion, object permanence, free space, and containment; on par with representations learnt by the most popular modern paradigm for visual representation learning which requires large datasets independently labeled for each new task. Expand

We show that embodied adversarial reinforcement learning agents playing Cache, a variant of hide-and-seek, in a high fidelity, interactive, environment, learn generalizable representations of their observations encoding information such as object permanence, free space, and containment. Expand

We provide a visualization library and web interface for the interactive visualization of hierarchical linguistic structure, seeking to minimize the cognitive load required to understand syntactic and semantic parses. Expand

This paper describes a case study about a multi-agent system for cooperative tasks, i.e. a mixing color task given three different sources of color. Expand