OpenAI

Source: https://openai.com

Found 1065 news

  • Introducing Activation Atlases
    OpenAI - 08:00 Mar 06, 2019
    We’ve created activation atlases (in collaboration with Google researchers), a new technique for visualizing what interactions between neurons can represent. As AI systems are deployed in increasingly sensitive contexts, having a better understanding of their internal decision-making processes will let us identify weaknesses and investigate failures.
  • Neural MMO: A massively multiagent game environment
    OpenAI - 08:00 Mar 04, 2019
    We’re releasing a Neural MMO, a massively multiagent game environment for reinforcement learning agents. Our platform supports a large, variable number of agents within a persistent and open-ended task. The inclusion of many agents and species leads to better exploration, divergent niche formation, and greater overall competence.
    Tags: Neural
  • Spinning Up in Deep RL: Workshop review
    OpenAI - 08:00 Feb 26, 2019
    On February 2, we held our first Spinning Up Workshop as part of our new education initiative at OpenAI.
    Tags: Workshop Spinning
  • AI safety needs social scientists
    OpenAI - 08:00 Feb 19, 2019
    We’ve written a paper arguing that long-term AI safety research needs social scientists to ensure AI alignment algorithms succeed when actual humans are involved. Properly aligning advanced AI systems with human values requires resolving many uncertainties related to the psychology of human rationality, emotion, and biases. The aim of this paper is to spark further collaboration between machine learning and social science researchers, and we plan to hire social scientists to work on this full time at OpenAI.
  • Better language models and their implications
    OpenAI - 08:00 Feb 14, 2019
    We’ve trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question answering, and summarization—all without task-specific training.
  • Computational limitations in robust classification and win-win results
    OpenAI - 08:00 Feb 04, 2019
  • OpenAI Fellows Summer 2018: Final projects
    OpenAI - 08:00 Dec 19, 2018
    Our 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.
  • How AI training scales
    OpenAI - 08:00 Dec 14, 2018
    We’ve discovered that the gradient noise scale, a simple statistical metric, predicts the parallelizability of neural network training on a wide range of tasks. Since complex tasks tend to have noisier gradients, increasingly large batch sizes are likely to become useful in the future, removing one potential limit to further growth of AI systems. More broadly, these results show that neural network training need not be considered a mysterious art, but can be rigorized and systematized.
  • Quantifying generalization in reinforcement learning
    OpenAI - 08:00 Dec 06, 2018
    We’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.
  • Spinning Up in Deep RL
    OpenAI - 08:00 Nov 08, 2018
    We’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.
    Tags: Spinning Deep
  • Learning concepts with energy functions
    OpenAI - 08:00 Nov 07, 2018
    We’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.
  • Plan online, learn offline: Efficient learning and exploration via model-based control
    OpenAI - 08:00 Nov 05, 2018
  • Reinforcement learning with prediction-based rewards
    OpenAI - 07:00 Oct 31, 2018
    We’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.
  • Learning complex goals with iterated amplification
    OpenAI - 07:00 Oct 22, 2018
    We’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.
  • OpenAI Scholars 2019: Applications open
    OpenAI - 07:00 Oct 11, 2018
    We 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.
    Tags: OpenAI Scholars
  • OpenAI Fellows Winter 2019 & Interns Summer 2019
    OpenAI - 07:00 Oct 09, 2018
    We are now accepting applications for OpenAI Fellows and Interns for 2019.
  • FFJORD: Free-form continuous dynamics for scalable reversible generative models
    OpenAI - 07:00 Oct 02, 2018
  • OpenAI Scholars 2018: Final projects
    OpenAI - 07:00 Sep 10, 2018
    Our first cohort of OpenAI Scholars has now completed the program.
    Tags: OpenAI Scholars
  • The International 2018: Results
    OpenAI - 07:00 Aug 23, 2018
    OpenAI Five lost two games against top Dota 2 players at The International in Vancouver this week, maintaining a good chance of winning for the first 20–35 minutes of both games.
    Tags: The International
  • Large-scale study of curiosity-driven learning
    OpenAI - 07:00 Aug 13, 2018

1065 items

Popular Tags