Institution
OpenAI
About: OpenAI is a based out in . It is known for research contribution in the topics: Reinforcement learning & Artificial neural network. The organization has 105 authors who have published 213 publications receiving 68067 citations. The organization is also known as: Open AI & OpenAI LP.
Topics: Reinforcement learning, Artificial neural network, Computer science, Language model, Deep learning
Papers
More filters
•
TL;DR: This paper proposed a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to earlier published flows, scales well to high-dimensional latent spaces, and demonstrated that a novel type of variational autoencoder, coupled with IAF, is competitive with neural autoregression models in terms of attained log-likelihood on natural images, while allowing significantly faster synthesis.
Abstract: The framework of normalizing flows provides a general strategy for flexible variational inference of posteriors over latent variables. We propose a new type of normalizing flow, inverse autoregressive flow (IAF), that, in contrast to earlier published flows, scales well to high-dimensional latent spaces. The proposed flow consists of a chain of invertible transformations, where each transformation is based on an autoregressive neural network. In experiments, we show that IAF significantly improves upon diagonal Gaussian approximate posteriors. In addition, we demonstrate that a novel type of variational autoencoder, coupled with IAF, is competitive with neural autoregressive models in terms of attained log-likelihood on natural images, while allowing significantly faster synthesis.
193 citations
•
OpenAI1, University of Cambridge2, McGill University3, University of Toronto4, University of Oxford5, Stanford University6, Google7, École Normale Supérieure8, École Polytechnique Fédérale de Lausanne9, Intel10, RAND Corporation11, Université de Montréal12, Eindhoven University of Technology13, The Turing Institute14, Center for a New American Security15, University of California16
TL;DR: This report suggests various steps that different stakeholders can take to improve the verifiability of claims made about AI systems and their associated development processes, with a focus on providing evidence about the safety, security, fairness, and privacy protection of AI systems.
Abstract: With the recent wave of progress in artificial intelligence (AI) has come a growing awareness of the large-scale impacts of AI systems, and recognition that existing regulations and norms in industry and academia are insufficient to ensure responsible AI development. In order for AI developers to earn trust from system users, customers, civil society, governments, and other stakeholders that they are building AI responsibly, they will need to make verifiable claims to which they can be held accountable. Those outside of a given organization also need effective means of scrutinizing such claims. This report suggests various steps that different stakeholders can take to improve the verifiability of claims made about AI systems and their associated development processes, with a focus on providing evidence about the safety, security, fairness, and privacy protection of AI systems. We analyze ten mechanisms for this purpose--spanning institutions, software, and hardware--and make recommendations aimed at implementing, exploring, or improving those mechanisms.
191 citations
•
TL;DR: This work exploits the full state observability in the simulator to train better policies which take as input only partial observations (RGBD images) and combines this method with domain randomization and shows real robot experiments for several tasks like picking, pushing, and moving a block.
Abstract: 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 on a physical system can be expensive and dangerous, which has sparked significant interest in learning control policies using a physics simulator. While several recent works have shown promising results in transferring policies trained in simulation to the real world, they often do not fully utilize the advantage of working with a simulator. In this work, we exploit the full state observability in the simulator to train better policies which take as input only partial observations (RGBD images). We do this by employing an actor-critic training algorithm in which the critic is trained on full states while the actor (or policy) gets rendered images as input. We show experimentally on a range of simulated tasks that using these asymmetric inputs significantly improves performance. Finally, we combine this method with domain randomization and show real robot experiments for several tasks like picking, pushing, and moving a block. We achieve this simulation to real world transfer without training on any real world data.
170 citations
••
26 Jun 2018TL;DR: The authors exploit the full state observability in the simulator to train better policies which take as input only partial observations (RGBD images) by employing an actor-critic training algorithm in which the critic is trained on full states while the actor (or policy) gets rendered images as input.
Abstract: 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 on a physical system can be expensive and dangerous, which has sparked significant interest in learning control policies using a physics simulator. While several recent works have shown promising results in transferring policies trained in simulation to the real world, they often do not fully utilize the advantage of working with a simulator. In this work, we exploit the full state observability in the simulator to train better policies which take as input only partial observations (RGBD images). We do this by employing an actor-critic training algorithm in which the critic is trained on full states while the actor (or policy) gets rendered images as input. We show experimentally on a range of simulated tasks that using these asymmetric inputs significantly improves performance. Finally, we combine this method with domain randomization and show real robot experiments for several tasks like picking, pushing, and moving a block. We achieve this simulation to real world transfer without training on any real world data.
170 citations
•
TL;DR: This paper proposed a simple approach for text-to-image generation based on a transformer that autoregressively models the text and image tokens as a single stream of data, which is competitive with previous domain-specific models when evaluated in a zero-shot fashion.
Abstract: Text-to-image generation has traditionally focused on finding better modeling assumptions for training on a fixed dataset. These assumptions might involve complex architectures, auxiliary losses, or side information such as object part labels or segmentation masks supplied during training. We describe a simple approach for this task based on a transformer that autoregressively models the text and image tokens as a single stream of data. With sufficient data and scale, our approach is competitive with previous domain-specific models when evaluated in a zero-shot fashion.
162 citations
Authors
Showing all 105 results
Name | H-index | Papers | Citations |
---|---|---|---|
Geoffrey E. Hinton | 157 | 414 | 409047 |
Pieter Abbeel | 126 | 589 | 70911 |
Ian Goodfellow | 85 | 137 | 135390 |
Ilya Sutskever | 75 | 131 | 235539 |
Kenneth O. Stanley | 60 | 223 | 16921 |
Phillip Isola | 48 | 101 | 45099 |
John Schulman | 48 | 67 | 30168 |
Jeff Clune | 48 | 140 | 21194 |
Wojciech Zaremba | 39 | 58 | 34954 |
Elizabeth A. Barnes | 39 | 132 | 5281 |
Igor Mordatch | 36 | 89 | 6604 |
Dario Amodei | 34 | 49 | 13108 |
Joel Lehman | 33 | 98 | 5588 |
Gillian K. Hadfield | 28 | 101 | 2420 |
Marcin Andrychowicz | 28 | 49 | 6638 |