Eric Kolve

Publications
Influence

Target-driven visual navigation in indoor scenes using deep reinforcement learning

Yuke Zhu, R. Mottaghi, +4 authors A. Farhadi
Computer Science
IEEE International Conference on Robotics and…
16 September 2016

We proposed a deep reinforcement learning (DRL) framework for target-driven visual navigation. Expand

AI2-THOR: An Interactive 3D Environment for Visual AI

Eric Kolve, R. Mottaghi, Daniel Gordon, Yuke Zhu, A. Gupta, Ali Farhadi
Computer Science
ArXiv
14 December 2017

We introduce The House Of inteRactions (THOR), a framework for visual AI research, available at this http URL AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate… Expand

A Diagram is Worth a Dozen Images

Aniruddha Kembhavi, Michael Salvato, Eric Kolve, Minjoon Seo, Hannaneh Hajishirzi, Ali Farhadi
Computer Science
ECCV
24 March 2016

We study the problem of diagram interpretation, the challenging task of identifying the structure of a diagram and the semantics of its constituents and their relationships. Expand

Visual Semantic Planning Using Deep Successor Representations

Yuke Zhu, Daniel Gordon, +5 authors A. Farhadi
Computer Science
IEEE International Conference on Computer Vision…
23 May 2017

A crucial capability of real-world intelligent agents is their ability to plan a sequence of actions to achieve their goals in the visual world. Expand

RoboTHOR: An Open Simulation-to-Real Embodied AI Platform

Matt Deitke, Winson Han, +10 authors A. Farhadi
Computer Science
IEEE/CVF Conference on Computer Vision and…
14 April 2020

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

Two Body Problem: Collaborative Visual Task Completion

Unnat Jain, Luca Weihs, +5 authors Aniruddha Kembhavi
Computer Science
IEEE/CVF Conference on Computer Vision and…
11 April 2019

We study the problem of learning to collaborate directly from pixels in AI2-THOR and demonstrate the benefits of explicit and implicit modes of communication to perform visual tasks. Expand

A Cordial Sync: Going Beyond Marginal Policies for Multi-Agent Embodied Tasks

Unnat Jain, Luca Weihs, +4 authors A. Schwing
Computer Science
ECCV
9 July 2020

We introduce the novel task FurnMove in which agents work together to move a piece of furniture through a living room to a goal. Expand

Artificial Agents Learn Flexible Visual Representations by Playing a Hiding Game

Luca Weihs, Aniruddha Kembhavi, +5 authors A. Farhadi
Computer Science
ArXiv
17 December 2019

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

LEARNING GENERALIZABLE VISUAL REPRESENTA-

TIONS VIA, Interactive Gameplay, +9 authors A. Farhadi
2021

A growing body of research suggests that embodied gameplay, prevalent not just in human cultures but across a variety of animal species including turtles and ravens, is critical in developing the… Expand

ManipulaTHOR: A Framework for Visual Object Manipulation

Kiana Ehsani, Winson Han, +5 authors R. Mottaghi
Computer Science
ArXiv
22 April 2021

We propose a framework for object manipulation built upon the physics-enabled, visually rich AI2-THOR framework and present a new challenge to the Embodied AI community known as ArmPointNav. Expand

Recommended Authors