5.6k citations · 19.9k across the 27 of their papers we have counts for
31 papers
GPT-4 Technical Report
OpenAI, Josh Achiam, Steven Adler +278
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-wor…
Evaluating Large Language Models Trained on Code
Mark Chen, Jerry Tworek, Heewoo Jun +55
We introduce Codex, a GPT language model fine-tuned on publicly available code from GitHub, and study its Python code-writing capabilities. A distinct production version of Codex p…
A Generalizable Approach to Learning Optimizers
Diogo Almeida, Clemens Winter, Jie Tang +1
A core issue with learning to optimize neural networks has been the lack of generalization to real world problems. To address this, we describe a system designed from a generalizat…
Asymmetric self-play for automatic goal discovery in robotic manipulation
OpenAI OpenAI, Matthias Plappert, Raul Sampedro +13
We train a single, goal-conditioned policy that can solve many robotic manipulation tasks, including tasks with previously unseen goals and objects. We rely on asymmetric self-play…
Predicting Sim-to-Real Transfer with Probabilistic Dynamics Models
Lei M. Zhang, Matthias Plappert, Wojciech Zaremba
We propose a method to predict the sim-to-real transfer performance of RL policies. Our transfer metric simplifies the selection of training setups (such as algorithm, hyperparamet…
Solving Rubik's Cube with a Robot Hand
OpenAI, Ilge Akkaya, Marcin Andrychowicz +16
We demonstrate that models trained only in simulation can be used to solve a manipulation problem of unprecedented complexity on a real robot. This is made possible by two key comp…
Learning Dexterous In-Hand Manipulation
OpenAI, Marcin Andrychowicz, Bowen Baker +14
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. The tra…
Multi-Goal Reinforcement Learning: Challenging Robotics Environments and Request for Research
Matthias Plappert, Marcin Andrychowicz, Alex Ray +9
The purpose of this technical report is two-fold. First of all, it introduces a suite of challenging continuous control tasks (integrated with OpenAI Gym) based on currently existi…
Asymmetric Actor Critic for Image-Based Robot Learning
Lerrel Pinto, Marcin Andrychowicz, Peter Welinder +2
Deep reinforcement learning (RL) has proven a powerful technique in many sequential decision making domains. However, Robotics poses many challenges for RL, most notably training o…
Sim-to-Real Transfer of Robotic Control with Dynamics Randomization
Xue Bin Peng, Marcin Andrychowicz, Wojciech Zaremba +1
Simulations are attractive environments for training agents as they provide an abundant source of data and alleviate certain safety concerns during the training process. But the be…
Domain Randomization and Generative Models for Robotic Grasping
Joshua Tobin, Lukas Biewald, Rocky Duan +8
Deep learning-based robotic grasping has made significant progress thanks to algorithmic improvements and increased data availability. However, state-of-the-art models are often tr…
Overcoming Exploration in Reinforcement Learning with Demonstrations
Ashvin Nair, Bob McGrew, Marcin Andrychowicz +2
Exploration in environments with sparse rewards has been a persistent problem in reinforcement learning (RL). Many tasks are natural to specify with a sparse reward, and manually s…
Hindsight Experience Replay
Marcin Andrychowicz, Filip Wolski, Alex Ray +7
Dealing with sparse rewards is one of the biggest challenges in Reinforcement Learning (RL). We present a novel technique called Hindsight Experience Replay which allows sample-eff…
Domain Randomization for Transferring Deep Neural Networks from Simulation to the Real World
Josh Tobin, Rachel Fong, Alex Ray +3
Bridging the 'reality gap' that separates simulated robotics from experiments on hardware could accelerate robotic research through improved data availability. This paper explores…
One-Shot Imitation Learning
Yan Duan, Marcin Andrychowicz, Bradly C. Stadie +5
Imitation learning has been commonly applied to solve different tasks in isolation. This usually requires either careful feature engineering, or a significant number of samples. Th…
Extensions and Limitations of the Neural GPU
Eric Price, Wojciech Zaremba, Ilya Sutskever
The Neural GPU is a recent model that can learn algorithms such as multi-digit binary addition and binary multiplication in a way that generalizes to inputs of arbitrary length. We…
Transfer from Simulation to Real World through Learning Deep Inverse Dynamics Model
Paul Christiano, Zain Shah, Igor Mordatch +5
Developing control policies in simulation is often more practical and safer than directly running experiments in the real world. This applies to policies obtained from planning and…
Improved Techniques for Training GANs
Tim Salimans, Ian Goodfellow, Wojciech Zaremba +3
We present a variety of new architectural features and training procedures that we apply to the generative adversarial networks (GANs) framework. We focus on two applications of GA…
OpenAI Gym
Greg Brockman, Vicki Cheung, Ludwig Pettersson +4
OpenAI Gym is a toolkit for reinforcement learning research. It includes a growing collection of benchmark problems that expose a common interface, and a website where people can s…
Learning Simple Algorithms from Examples
Wojciech Zaremba, Tomas Mikolov, Armand Joulin +1
We present an approach for learning simple algorithms such as copying, multi-digit addition and single digit multiplication directly from examples. Our framework consists of a set…
Sequence Level Training with Recurrent Neural Networks
Marc'Aurelio Ranzato, Sumit Chopra, Michael Auli +1
Many natural language processing applications use language models to generate text. These models are typically trained to predict the next word in a sequence, given the previous wo…
Convolutional networks and learning invariant to homogeneous multiplicative scalings
Mark Tygert, Arthur Szlam, Soumith Chintala +3
The conventional classification schemes -- notably multinomial logistic regression -- used in conjunction with convolutional networks (convnets) are classical in statistics, design…
Reinforcement Learning Neural Turing Machines - Revised
Wojciech Zaremba, Ilya Sutskever
The Neural Turing Machine (NTM) is more expressive than all previously considered models because of its external memory. It can be viewed as a broader effort to use abstract extern…
Addressing the Rare Word Problem in Neural Machine Translation
Minh-Thang Luong, Ilya Sutskever, Quoc V. Le +2
Neural Machine Translation (NMT) is a new approach to machine translation that has shown promising results that are comparable to traditional approaches. A significant weakness in…