Browse press releases
The newest releases come first, each with its full text here and a link to its original. Try the filters to narrow them down.
- OpenAIFaulty reward functions in the wildCompanies: OpenAIReinforcement learning algorithms can break in surprising, counterintuitive ways. In this post we’ll explore one failure mode, which is where you misspecify your reward function.
- OpenAIUniverseCompanies: OpenAIWe’re releasing Universe, a software platform for measuring and training an AI’s general intelligence across the world’s supply of games, websites and other applications.
- OpenAIOpenAI and MicrosoftCompanies: OpenAIMicrosoftWe’re working with Microsoft to start running most of our large-scale experiments on Azure.
- OpenAI#Exploration: A study of count-based exploration for deep reinforcement learningCompanies: OpenAIOpenAI Abstract Count-based exploration algorithms are known to perform near-optimally when used in conjunction with tabular reinforcement learning (RL) methods for solving small discrete Markov decision processes (MDPs). It is generally thought that count-based methods cannot be applied in high-dimensional state spaces, since most states will only occur once. Recent deep RL exploration strategies are able to deal wi
- OpenAIOn the quantitative analysis of decoder-based generative modelsCompanies: OpenAIAbstract The past several years have seen remarkable progress in generative models which produce convincing samples of images and other modalities. A shared component of many powerful generative models is a decoder network, a parametric deep neural net that defines a generative distribution. Examples include variational autoencoders, generative adversarial networks, and generative moment matching networks. Unfortunat
- OpenAIA connection between generative adversarial networks, inverse reinforcement learning, and energy-based modelsCompanies: OpenAIAbstract Generative adversarial networks (GANs) are a recently proposed class of generative models in which a generator is trained to optimize a cost function that is being simultaneously learned by a discriminator. While the idea of learning cost functions is relatively new to the field of generative modeling, learning costs has long been studied in control and reinforcement learning (RL) domains, typically for imit
- OpenAIRL²: Fast reinforcement learning via slow reinforcement learningCompanies: OpenAIAbstract Deep reinforcement learning (deep RL) has been successful in learning sophisticated behaviors automatically; however, the learning process requires a huge number of trials. In contrast, animals can learn new tasks in just a few trials, benefiting from their prior knowledge about the world. This paper seeks to bridge this gap. Rather than designing a "fast" reinforcement learning algorithm, we propose to repr
- OpenAIVariational lossy autoencoderCompanies: OpenAIAbstract Representation learning seeks to expose certain aspects of observed data in a learned representation that’s amenable to downstream tasks like classification. For instance, a good representation for 2D images might be one that describes only global structure and discards information about detailed texture. In this paper, we present a simple but principled method to learn such global representations by combini
- OpenAIExtensions and limitations of the neural GPUCompanies: OpenAIAbstract 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 show that there are two simple ways of improving the performance of the Neural GPU: by carefully designing a curriculum, and by increasing model size. The latter requires a memory efficient implementation, as a naive implementatio
- OpenAISemi-supervised knowledge transfer for deep learning from private training dataCompanies: OpenAIAbstract Some machine learning applications involve training data that is sensitive, such as the medical histories of patients in a clinical trial. A model may inadvertently and implicitly store some of its training data; careful analysis of the model may therefore reveal sensitive information. To address this problem, we demonstrate a generally applicable approach to providing strong privacy guarantees for training
- OpenAIReport from the self-organizing conferenceCompanies: OpenAILast week we hosted over a hundred and fifty AI practitioners in our offices for our first self-organizing conference on machine learning.
- OpenAITransfer from simulation to real world through learning deep inverse dynamics modelCompanies: OpenAIAbstract 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 optimization, and even more so to policies obtained from reinforcement learning, which is often very data demanding. However, a policy that succeeds in simulation often doesn’t work when deployed on a real robot. Nevertheless, oft