Training Verifiers to Solve Math Word Problems

2 code implementations • 27 Oct 2021 • Karl Cobbe, Vineet Kosaraju, Mohammad Bavarian, Mark Chen, Heewoo Jun, Lukasz Kaiser, Matthias Plappert, Jerry Tworek, Jacob Hilton, Reiichiro Nakano, Christopher Hesse, John Schulman

State-of-the-art language models can match human performance on many tasks, but they still struggle to robustly perform multi-step mathematical reasoning.

GSM8K Mathematical Reasoning

Evaluating Large Language Models Trained on Code

8 code implementations • 7 Jul 2021 • Mark Chen, Jerry Tworek, Heewoo Jun, Qiming Yuan, Henrique Ponde de Oliveira Pinto, Jared Kaplan, Harri Edwards, Yuri Burda, Nicholas Joseph, Greg Brockman, Alex Ray, Raul Puri, Gretchen Krueger, Michael Petrov, Heidy Khlaaf, Girish Sastry, Pamela Mishkin, Brooke Chan, Scott Gray, Nick Ryder, Mikhail Pavlov, Alethea Power, Lukasz Kaiser, Mohammad Bavarian, Clemens Winter, Philippe Tillet, Felipe Petroski Such, Dave Cummings, Matthias Plappert, Fotios Chantzis, Elizabeth Barnes, Ariel Herbert-Voss, William Hebgen Guss, Alex Nichol, Alex Paino, Nikolas Tezak, Jie Tang, Igor Babuschkin, Suchir Balaji, Shantanu Jain, William Saunders, Christopher Hesse, Andrew N. Carr, Jan Leike, Josh Achiam, Vedant Misra, Evan Morikawa, Alec Radford, Matthew Knight, Miles Brundage, Mira Murati, Katie Mayer, Peter Welinder, Bob McGrew, Dario Amodei, Sam McCandlish, Ilya Sutskever, Wojciech Zaremba

We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities.

Code Generation Language Modelling +1

Asymmetric self-play for automatic goal discovery in robotic manipulation

no code implementations • 13 Jan 2021 • OpenAI OpenAI, Matthias Plappert, Raul Sampedro, Tao Xu, Ilge Akkaya, Vineet Kosaraju, Peter Welinder, Ruben D'Sa, Arthur Petron, Henrique Ponde de Oliveira Pinto, Alex Paino, Hyeonwoo Noh, Lilian Weng, Qiming Yuan, Casey Chu, Wojciech Zaremba

We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects.

Predicting Sim-to-Real Transfer with Probabilistic Dynamics Models

no code implementations • 27 Sep 2020 • Lei M. Zhang, Matthias Plappert, Wojciech Zaremba

We further show that the transfer metric can predict the effect of training setups on policy transfer performance.

Solving Rubik's Cube with a Robot Hand

1 code implementation • 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

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

30 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

Parameter Space Noise for Exploration

10 code implementations • ICLR 2018 • Matthias Plappert, Rein Houthooft, Prafulla Dhariwal, Szymon Sidor, Richard Y. Chen, Xi Chen, Tamim Asfour, Pieter Abbeel, Marcin Andrychowicz

Combining parameter noise with traditional RL methods allows to combine the best of both worlds.

Continuous Control reinforcement-learning +1

Learning a bidirectional mapping between human whole-body motion and natural language using deep recurrent neural networks

no code implementations • 18 May 2017 • Matthias Plappert, Christian Mandery, Tamim Asfour

We evaluate our approach on 2, 846 human whole-body motions and 6, 187 natural language descriptions thereof from the KIT Motion-Language Dataset.

Feature Engineering Machine Translation

The KIT Motion-Language Dataset

no code implementations • 13 Jul 2016 • Matthias Plappert, Christian Mandery, Tamim Asfour

Linking human motion and natural language is of great interest for the generation of semantic representations of human activities as well as for the generation of robot activities based on natural language input.

Classification of Human Whole-Body Motion using Hidden Markov Models

no code implementations • 5 May 2016 • Matthias Plappert

These features are then used to perform the multi-label classification using two different approaches.

Classification General Classification +1