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.
- OpenAISpam detection in the physical worldCompanies: OpenAIWe’ve created the world’s first Spam-detecting AI trained entirely in simulation and deployed on a physical robot.
- OpenAIEvolution strategies as a scalable alternative to reinforcement learningCompanies: OpenAIWe’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e.g. Atari/MuJoCo), while overcoming many of RL’s inconveniences.
- OpenAIOne-shot imitation learningCompanies: OpenAIAbstract 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. This is far from what we desire: ideally, robots should be able to learn from very few demonstrations of any given task, and instantly generalize to new situations of the same task, without requiring task-specific engineering. In thi
- OpenAIDistillCompanies: OpenAIWe’re excited to support today’s launch of Distill, a new kind of journal aimed at excellent communication of machine learning results (novel or existing).
- OpenAILearning to communicateCompanies: OpenAIIn this post we’ll outline new OpenAI research in which agents develop their own language.
- OpenAIEmergence of grounded compositional language in multi-agent populationsCompanies: OpenAIAbstract By capturing statistical patterns in large corpora, machine learning has enabled significant advances in natural language processing, including in machine translation, question answering, and sentiment analysis. However, for agents to intelligently interact with humans, simply capturing the statistical patterns is insufficient. In this paper we investigate if, and how, grounded compositional language can eme
- OpenAIPrediction and control with temporal segment modelsCompanies: OpenAIAbstract We introduce a method for learning the dynamics of complex nonlinear systems based on deep generative models over temporal segments of states and actions. Unlike dynamics models that operate over individual discrete timesteps, we learn the distribution over future state trajectories conditioned on past state, past action, and planned future action trajectories, as well as a latent prior over action trajector
- OpenAIThird-person imitation learningCompanies: OpenAIAbstract Reinforcement learning (RL) makes it possible to train agents capable of achieving sophisticated goals in complex and uncertain environments. A key difficulty in reinforcement learning is specifying a reward function for the agent to optimize. Traditionally, imitation learning in RL has been used to overcome this problem. Unfortunately, hitherto imitation learning methods tend to require that demonstrations
- OpenAIAttacking machine learning with adversarial examplesCompanies: OpenAIAdversarial examples are inputs to machine learning models that an attacker has intentionally designed to cause the model to make a mistake; they’re like optical illusions for machines. In this post we’ll show how adversarial examples work across different mediums, and will discuss why securing systems against them can be difficult.
- OpenAIAdversarial attacks on neural network policiesCompanies: OpenAIOpenAI Abstract Machine learning classifiers are known to be vulnerable to inputs maliciously constructed by adversaries to force misclassification. Such adversarial examples have been extensively studied in the context of computer vision applications. In this work, we show adversarial attacks are also effective when targeting neural network policies in reinforcement learning. Specifically, we show existing adversari
- OpenAITeam updateCompanies: OpenAIThe OpenAI team is now 45 people. Together, we’re pushing the frontier of AI capabilities—whether by validating novel ideas, creating new software systems, or deploying machine learning on robots.
- OpenAIPixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other modificationsCompanies: OpenAIAbstract PixelCNNs are a recently proposed class of powerful generative models with tractable likelihood. Here we discuss our implementation of PixelCNNs which we make available at this https URL(opens in a new window) . Our implementation contains a number of modifications to the original model that both simplify its structure and improve its performance. 1) We use a discretized logistic mixture likelihood on the p