PSP-HDRI$+$: A Synthetic Dataset Generator for Pre-Training of Human-Centric Computer Vision Models

1 code implementation • 11 Jul 2022 • Salehe Erfanian Ebadi, Saurav Dhakad, Sanjay Vishwakarma, Chunpu Wang, You-Cyuan Jhang, Maciek Chociej, Adam Crespi, Alex Thaman, Sujoy Ganguly

We introduce a new synthetic data generator PSP-HDRI$+$ that proves to be a superior pre-training alternative to ImageNet and other large-scale synthetic data counterparts.

Keypoint Estimation

Solving Rubik's Cube with a Robot Hand

2 code implementations • 16 Oct 2019 • OpenAI, Ilge Akkaya, Marcin Andrychowicz, Maciek Chociej, Mateusz Litwin, Bob McGrew, Arthur Petron, Alex Paino, Matthias Plappert, Glenn Powell, Raphael Ribas, Jonas Schneider, Nikolas Tezak, Jerry Tworek, Peter Welinder, Lilian Weng, Qiming Yuan, Wojciech Zaremba, Lei Zhang

We demonstrate that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot.

Meta-Learning Rubik's Cube

ORRB -- OpenAI Remote Rendering Backend

1 code implementation • 26 Jun 2019 • Maciek Chociej, Peter Welinder, Lilian Weng

We present the OpenAI Remote Rendering Backend (ORRB), a system that allows fast and customizable rendering of robotics environments.

Learning Dexterous In-Hand Manipulation

no code implementations • 1 Aug 2018 • OpenAI, Marcin Andrychowicz, Bowen Baker, Maciek Chociej, Rafal Jozefowicz, Bob McGrew, Jakub Pachocki, Arthur Petron, Matthias Plappert, Glenn Powell, Alex Ray, Jonas Schneider, Szymon Sidor, Josh Tobin, Peter Welinder, Lilian Weng, Wojciech Zaremba

We use reinforcement learning (RL) to learn dexterous in-hand manipulation policies which can perform vision-based object reorientation on a physical Shadow Dexterous Hand.

Friction reinforcement-learning +1

Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research

28 code implementations • 26 Feb 2018 • Matthias Plappert, Marcin Andrychowicz, Alex Ray, Bob McGrew, Bowen Baker, Glenn Powell, Jonas Schneider, Josh Tobin, Maciek Chociej, Peter Welinder, Vikash Kumar, Wojciech Zaremba

The purpose of this technical report is two-fold.

Continuous Control Multi-Goal Reinforcement Learning +3