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.
- OpenAIComputational limitations in robust classification and win-win resultsCompanies: OpenAIAbstract We continue the study of statistical/computational tradeoffs in learning robust classifiers, following the recent work of Bubeck, Lee, Price and Razenshteyn who showed examples of classification tasks where (a) an efficient robust classifier exists, in the small-perturbation regime; (b) a non-robust classifier can be learned efficiently; but (c) it is computationally hard to learn a robust classifier, assumi
- OpenAIOpenAI Fellows Summer 2018: Final projectsCompanies: OpenAIOur first cohort of OpenAI Fellows has concluded, with each Fellow going from a machine learning beginner to core OpenAI contributor in the course of a 6-month apprenticeship.
- OpenAIQuantifying generalization in reinforcement learningCompanies: OpenAIWe’re releasing CoinRun, a training environment which provides a metric for an agent’s ability to transfer its experience to novel situations and has already helped clarify a longstanding puzzle in reinforcement learning. CoinRun strikes a desirable balance in complexity: the environment is simpler than traditional platformer games like Sonic the Hedgehog but still poses a worthy generalization challenge for state of the art algorithms.
- OpenAISpinning Up in Deep RLCompanies: OpenAIWe’re releasing Spinning Up in Deep RL, an educational resource designed to let anyone learn to become a skilled practitioner in deep reinforcement learning. Spinning Up consists of crystal-clear examples of RL code, educational exercises, documentation, and tutorials.
- OpenAILearning concepts with energy functionsCompanies: OpenAIWe’ve developed an energy-based model that can quickly learn to identify and generate instances of concepts, such as near, above, between, closest, and furthest, expressed as sets of 2d points. Our model learns these concepts after only five demonstrations. We also show cross-domain transfer: we use concepts learned in a 2d particle environment to solve tasks on a 3-dimensional physics-based robot.
- OpenAIPlan online, learn offline: Efficient learning and exploration via model-based controlCompanies: OpenAIAbstract We propose a plan online and learn offline (POLO) framework for the setting where an agent, with an internal model, needs to continually act and learn in the world. Our work builds on the synergistic relationship between local model-based control, global value function learning, and exploration. We study how local trajectory optimization can cope with approximation errors in the value function, and can stabi
- OpenAIReinforcement learning with prediction-based rewardsCompanies: OpenAIWe’ve developed Random Network Distillation (RND), a prediction-based method for encouraging reinforcement learning agents to explore their environments through curiosity, which for the first time exceeds average human performance on Montezuma’s Revenge.
- OpenAILearning complex goals with iterated amplificationCompanies: OpenAIWe’re proposing an AI safety technique called iterated amplification that lets us specify complicated behaviors and goals that are beyond human scale, by demonstrating how to decompose a task into simpler sub-tasks, rather than by providing labeled data or a reward function. Although this idea is in its very early stages and we have only completed experiments on simple toy algorithmic domains, we’ve decided to present it in its preliminary state because we think it could prove to be a scalable approach to AI safety.
- OpenAIOpenAI Scholars 2019: Applications openCompanies: OpenAIWe are now accepting applications for our second cohort of OpenAI Scholars, a program where we provide 6–10 stipends and mentorship to individuals from underrepresented groups to study deep learning full-time for 3 months and open-source a project.
- OpenAILarge-scale study of curiosity-driven learningCompanies: OpenAIOpenAI Abstract Reinforcement learning algorithms rely on carefully engineering environment rewards that are extrinsic to the agent. However, annotating each environment with hand-designed, dense rewards is not scalable, motivating the need for developing reward functions that are intrinsic to the agent. Curiosity is a type of intrinsic reward function which uses prediction error as reward signal. In this paper: (a)
- OpenAILearning dexterityCompanies: OpenAIWe’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
- OpenAIVariational option discovery algorithmsCompanies: OpenAIOpenAI Abstract We explore methods for option discovery based on variational inference and make two algorithmic contributions. First: we highlight a tight connection between variational option discovery methods and variational autoencoders, and introduce Variational Autoencoding Learning of Options by Reinforcement (VALOR), a new method derived from the connection. In VALOR, the policy encodes contexts from a noise d