E
Eric Kolve
Researcher at Allen Institute for Artificial Intelligence
Publications - 24
Citations - 2900
Eric Kolve is an academic researcher from Allen Institute for Artificial Intelligence. The author has contributed to research in topics: Reinforcement learning & Embodied cognition. The author has an hindex of 11, co-authored 22 publications receiving 1950 citations.
Papers
More filters
Proceedings ArticleDOI
Target-driven visual navigation in indoor scenes using deep reinforcement learning
TL;DR: This article proposed an actor-critic model whose policy is a function of the goal as well as the current state, which allows better generalization and generalizes across targets and scenes.
Posted Content
AI2-THOR: An Interactive 3D Environment for Visual AI
TL;DR: AI2-THOR consists of near photo-realistic 3D indoor scenes, where AI agents can navigate in the scenes and interact with objects to perform tasks and facilitate building visually intelligent models.
Proceedings ArticleDOI
RoboTHOR: An Open Simulation-to-Real Embodied AI Platform
Matt Deitke,Winson Han,Alvaro Herrasti,Aniruddha Kembhavi,Eric Kolve,Roozbeh Mottaghi,Jordi Salvador,Dustin Schwenk,Eli VanderBilt,Matthew Wallingford,Luca Weihs,Mark Yatskar,Ali Farhadi +12 more
TL;DR: RoboTHOR as discussed by the authors is a framework for simulation-to-real embodied computer vision that allows researchers across the globe to remotely test their embodied models in the physical world and demonstrate that there exists a significant gap between the performance of models trained in simulation when they are tested in both simulations and their carefully constructed physical analogs.
Book ChapterDOI
A Diagram is Worth a Dozen Images
Aniruddha Kembhavi,Mike Salvato,Eric Kolve,Minjoon Seo,Hannaneh Hajishirzi,Ali Farhadi,Ali Farhadi +6 more
TL;DR: An LSTM-based method for syntactic parsing of diagrams and a DPG-based attention model for diagram question answering are devised and a new dataset of diagrams with exhaustive annotations of constituents and relationships is compiled.
Proceedings ArticleDOI
Visual Semantic Planning Using Deep Successor Representations
Yuke Zhu,Daniel Gordon,Eric Kolve,Dieter Fox,Li Fei-Fei,Abhinav Gupta,Roozbeh Mottaghi,Ali Farhadi +7 more
TL;DR: In this paper, the authors address the problem of visual semantic planning, which involves predicting a sequence of actions from visual observations that transform a dynamic environment from an initial state to a goal state.