Get our free extension to see links to code for papers anywhere online!

Chrome logo Add to Chrome

Firefox logo Add to Firefox

Picture for Pulkit Agrawal

Rapid Locomotion via Reinforcement Learning


May 05, 2022
Gabriel B Margolis, Ge Yang, Kartik Paigwar, Tao Chen, Pulkit Agrawal

* Accepted for publication at Robotics: Science and Systems (RSS) 2022 

  Access Paper or Ask Questions

Bilinear value networks


Apr 28, 2022
Zhang-Wei Hong, Ge Yang, Pulkit Agrawal


  Access Paper or Ask Questions

An Integrated Design Pipeline for Tactile Sensing Robotic Manipulators


Apr 14, 2022
Lara Zlokapa, Yiyue Luo, Jie Xu, Michael Foshey, Kui Wu, Pulkit Agrawal, Wojciech Matusik


  Access Paper or Ask Questions

Topological Experience Replay


Mar 29, 2022
Zhang-Wei Hong, Tao Chen, Yen-Chen Lin, Joni Pajarinen, Pulkit Agrawal


  Access Paper or Ask Questions

Stubborn: A Strong Baseline for Indoor Object Navigation


Mar 14, 2022
Haokuan Luo, Albert Yue, Zhang-Wei Hong, Pulkit Agrawal


  Access Paper or Ask Questions

Neural Descriptor Fields: SE(3)-Equivariant Object Representations for Manipulation


Dec 09, 2021
Anthony Simeonov, Yilun Du, Andrea Tagliasacchi, Joshua B. Tenenbaum, Alberto Rodriguez, Pulkit Agrawal, Vincent Sitzmann

* Website: https://yilundu.github.io/ndf/. First two authors contributed equally (order determined by coin flip), last two authors equal advising 

  Access Paper or Ask Questions

A System for General In-Hand Object Re-Orientation


Nov 04, 2021
Tao Chen, Jie Xu, Pulkit Agrawal

* Accepted as an oral paper by CORL (Conference on Robot Learning); Keywords: dexterous manipulation, in-hand manipulation, object reorientation 

  Access Paper or Ask Questions

Learning to Jump from Pixels


Oct 28, 2021
Gabriel B. Margolis, Tao Chen, Kartik Paigwar, Xiang Fu, Donghyun Kim, Sangbae Kim, Pulkit Agrawal

* Accepted for publication at Conference on Robot Learning (CoRL) 2021 

  Access Paper or Ask Questions

Equivariant Contrastive Learning


Oct 28, 2021
Rumen Dangovski, Li Jing, Charlotte Loh, Seungwook Han, Akash Srivastava, Brian Cheung, Pulkit Agrawal, Marin Soljačić

* 17 pages, 5 figures 

  Access Paper or Ask Questions

An End-to-End Differentiable Framework for Contact-Aware Robot Design


Jul 15, 2021
Jie Xu, Tao Chen, Lara Zlokapa, Michael Foshey, Wojciech Matusik, Shinjiro Sueda, Pulkit Agrawal

* Robotics: Science and Systems 

  Access Paper or Ask Questions

3D Neural Scene Representations for Visuomotor Control


Jul 08, 2021
Yunzhu Li, Shuang Li, Vincent Sitzmann, Pulkit Agrawal, Antonio Torralba

* First two authors contributed equally. Project Page: https://3d-representation-learning.github.io/nerf-dy/ 

  Access Paper or Ask Questions

Learning Task Informed Abstractions


Jun 30, 2021
Xiang Fu, Ge Yang, Pulkit Agrawal, Tommi Jaakkola

* 8 pages, 12 figures 

  Access Paper or Ask Questions

Residual Model Learning for Microrobot Control


Apr 01, 2021
Joshua Gruenstein, Tao Chen, Neel Doshi, Pulkit Agrawal


  Access Paper or Ask Questions

The Low-Rank Simplicity Bias in Deep Networks


Mar 18, 2021
Minyoung Huh, Hossein Mobahi, Richard Zhang, Brian Cheung, Pulkit Agrawal, Phillip Isola


  Access Paper or Ask Questions

A Long Horizon Planning Framework for Manipulating Rigid Pointcloud Objects


Nov 16, 2020
Anthony Simeonov, Yilun Du, Beomjoon Kim, Francois R. Hogan, Joshua Tenenbaum, Pulkit Agrawal, Alberto Rodriguez

* Conference on Robot Learning (CoRL 2020): Project website: https://anthonysimeonov.github.io/rpo-planning-framework/ 

  Access Paper or Ask Questions

OPAL: Offline Primitive Discovery for Accelerating Offline Reinforcement Learning


Oct 27, 2020
Anurag Ajay, Aviral Kumar, Pulkit Agrawal, Sergey Levine, Ofir Nachum

* https://sites.google.com/view/opal-iclr 

  Access Paper or Ask Questions

AdaScale SGD: A User-Friendly Algorithm for Distributed Training


Jul 09, 2020
Tyler B. Johnson, Pulkit Agrawal, Haijie Gu, Carlos Guestrin

* ICML 2020 

  Access Paper or Ask Questions

Towards Practical Multi-Object Manipulation using Relational Reinforcement Learning


Dec 23, 2019
Richard Li, Allan Jabri, Trevor Darrell, Pulkit Agrawal

* 10 pages, 4 figures and 1 table in main article, 3 figures and 3 tables in appendix. Supplementary website and videos at https://richardrl.github.io/relational-rl/ 

  Access Paper or Ask Questions

Superposition of many models into one


Feb 14, 2019
Brian Cheung, Alex Terekhov, Yubei Chen, Pulkit Agrawal, Bruno Olshausen


  Access Paper or Ask Questions

Investigating Human Priors for Playing Video Games


Jul 25, 2018
Rachit Dubey, Pulkit Agrawal, Deepak Pathak, Thomas L. Griffiths, Alexei A. Efros

* ICML 2018 
* ICML 2018 

  Access Paper or Ask Questions

Learning Instance Segmentation by Interaction


Jun 21, 2018
Deepak Pathak, Yide Shentu, Dian Chen, Pulkit Agrawal, Trevor Darrell, Sergey Levine, Jitendra Malik

* Website at https://pathak22.github.io/seg-by-interaction/ 

  Access Paper or Ask Questions

Zero-Shot Visual Imitation


Apr 23, 2018
Deepak Pathak, Parsa Mahmoudieh, Guanghao Luo, Pulkit Agrawal, Dian Chen, Yide Shentu, Evan Shelhamer, Jitendra Malik, Alexei A. Efros, Trevor Darrell

* Oral presentation at ICLR 2018. Website at https://pathak22.github.io/zeroshot-imitation/ 

  Access Paper or Ask Questions

A Computer Vision Pipeline for Automated Determination of Cardiac Structure and Function and Detection of Disease by Two-Dimensional Echocardiography


Jan 12, 2018
Jeffrey Zhang, Sravani Gajjala, Pulkit Agrawal, Geoffrey H. Tison, Laura A. Hallock, Lauren Beussink-Nelson, Eugene Fan, Mandar A. Aras, ChaRandle Jordan, Kirsten E. Fleischmann, Michelle Melisko, Atif Qasim, Alexei Efros, Sanjiv J. Shah, Ruzena Bajcsy, Rahul C. Deo

* 9 figures, 2 tables 

  Access Paper or Ask Questions

Learning to Perform Physics Experiments via Deep Reinforcement Learning


Aug 17, 2017
Misha Denil, Pulkit Agrawal, Tejas D Kulkarni, Tom Erez, Peter Battaglia, Nando de Freitas


  Access Paper or Ask Questions

Curiosity-driven Exploration by Self-supervised Prediction


May 15, 2017
Deepak Pathak, Pulkit Agrawal, Alexei A. Efros, Trevor Darrell

* In ICML 2017. Website at https://pathak22.github.io/noreward-rl/ 

  Access Paper or Ask Questions

Combining Self-Supervised Learning and Imitation for Vision-Based Rope Manipulation


Mar 06, 2017
Ashvin Nair, Dian Chen, Pulkit Agrawal, Phillip Isola, Pieter Abbeel, Jitendra Malik, Sergey Levine

* 8 pages, accepted to International Conference on Robotics and Automation (ICRA) 2017 

  Access Paper or Ask Questions

Learning to Poke by Poking: Experiential Learning of Intuitive Physics


Feb 15, 2017
Pulkit Agrawal, Ashvin Nair, Pieter Abbeel, Jitendra Malik, Sergey Levine

* NIPS 2016 

  Access Paper or Ask Questions

What makes ImageNet good for transfer learning?


Dec 10, 2016
Minyoung Huh, Pulkit Agrawal, Alexei A. Efros


  Access Paper or Ask Questions

Human Pose Estimation with Iterative Error Feedback


Jun 12, 2016
Joao Carreira, Pulkit Agrawal, Katerina Fragkiadaki, Jitendra Malik


  Access Paper or Ask Questions

Learning Visual Predictive Models of Physics for Playing Billiards


Jan 19, 2016
Katerina Fragkiadaki, Pulkit Agrawal, Sergey Levine, Jitendra Malik


  Access Paper or Ask Questions