Learning to communicate
In this post we’ll outline new OpenAI research in which agents develop their own language.
按时间倒序汇集的来源索引。展示关键元数据并引导直达原始报道。
In this post we’ll outline new OpenAI research in which agents develop their own language.
AI 速览 多智能体群体中自发涌现出具有基础语义的组合式语言。
AI 速览 提出时序分段模型,用于序列预测与控制。
AI 速览 第三人称模仿学习。
Adversarial 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.
AI 速览 对抗性攻击可针对神经网络策略,威胁强化学习智能体的决策安全。
The 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.
AI 速览 OpenAI提出PixelCNN++,通过离散化逻辑混合似然及其他改进优化PixelCNN。
Reinforcement 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.
We’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.
AI 速览 研究探讨了基于计数的探索方法在深度强化学习中的应用。
We’re working with Microsoft to start running most of our large-scale experiments on Azure.
AI 速览 对基于解码器的生成模型进行定量分析。
AI 速览 生成对抗网络、逆强化学习与基于能量的模型之间存在理论联系。
AI 速览 RL²提出通过慢速强化学习实现快速强化学习,即用慢速RL训练一个循环神经网络作为快速RL算法,使其能在新任务上快速适应。
AI 速览 变分有损自编码器(Variational Lossy Autoencoder)是一种结合变分自编码器与有损压缩思想的方法,旨在学习数据的紧凑表示。
AI 速览 神经GPU的扩展与局限性。
AI 速览 提出半监督知识迁移方法,利用私有训练数据训练深度学习模型。
Last week we hosted over a hundred and fifty AI practitioners in our offices for our first self-organizing conference on machine learning.
AI 速览 通过深度学习逆动力学模型,实现从仿真到真实世界的迁移。
Deep learning is an empirical science, and the quality of a group’s infrastructure is a multiplier on progress. Fortunately, today’s open-source ecosystem makes it possible for anyone to build great deep learning infrastructure.
The latest information about the Unconference is now available at the Unconference wiki, which will be periodically updated with more information for attendees.
We’ve hired more great people to help us achieve our goals. Welcome, everyone!
Impactful scientific work requires working on the right problems—problems which are not just interesting, but whose solutions matter.
We (along with researchers from Berkeley and Stanford) are co-authors on today’s paper led by Google Brain researchers, Concrete Problems in AI Safety. The paper explores many research problems around ensuring that modern machine learning systems operate as intended.
OpenAI’s mission is to build safe AI, and ensure AI’s benefits are as widely and evenly distributed as possible.
This post describes four projects that share a common theme of enhancing or using generative models, a branch of unsupervised learning techniques in machine learning. In addition to describing our work, this post will tell you a bit more about generative models: what they are, why they are important, and where they might be going.
We’d like to welcome the latest set of team members to OpenAI (and we’re still hiring!)
AI 速览 提出针对半监督文本分类的对抗训练方法。
We’re releasing the public beta of OpenAI Gym, a toolkit for developing and comparing reinforcement learning (RL) algorithms. It consists of a growing suite of environments (from simulated robots to Atari games), and a site for comparing and reproducing results.