Large-scale study of curiosity-driven learning
AI 速览 大规模研究探讨好奇心驱动的学习机制。
围绕「开发」分类汇集的全球近期技术动态与前沿报道。
AI 速览 大规模研究探讨好奇心驱动的学习机制。
Yesterday, OpenAI Five won a best-of-three against a team of 99.95th percentile Dota players: Blitz, Cap, Fogged, Merlini, and MoonMeander—four of whom have played Dota professionally—in front of a live audience and 100,000 concurrent livestream viewers.
We’ve trained a human-like robot hand to manipulate physical objects with unprecedented dexterity.
AI 速览 变分选项发现算法。
Our first class of OpenAI Scholars is underway, and you can now follow along as this group of experienced software developers becomes machine learning practitioners.
The OpenAI Five Benchmark match is now over!
Our team of five neural networks, OpenAI Five, has started to defeat amateur human teams at Dota 2.
The first run of our Retro Contest—exploring the development of algorithms that can generalize from previous experience—is now complete.
We’ve obtained state-of-the-art results on a suite of diverse language tasks with a scalable, task-agnostic system, which we’re also releasing. Our approach is a combination of two existing ideas: transformers and unsupervised pre-training. These results provide a convincing example that pairing supervised learning methods with unsupervised pre-training works very well; this is an idea that many have explored in the past, and we hope our result motivates further research into applying this idea on larger and more d
AI 速览 GamePad:一个用于定理证明的学习环境。
We’re releasing the full version of Gym Retro, a platform for reinforcement learning research on games. This brings our publicly-released game count from around 70 Atari games and 30 Sega games to over 1,000 games across a variety of backing emulators. We’re also releasing the tool we use to add new games to the platform.
AI 速览 DeepMind提出新强化学习基准Gotta Learn Fast,用于评估智能体的泛化能力。
We’re launching a transfer learning contest that measures a reinforcement learning algorithm’s ability to generalize from previous experience.
AI 速览 提出动作相关因子化基线方法,用于策略梯度中的方差缩减。
AI 速览 提出利用最优传输改进GANs的方法。
AI 速览 首尔大学等机构提出一阶元学习算法,无需二阶梯度即可实现与MAML相当的少样本学习性能。
We’ve developed a simple meta-learning algorithm called Reptile which works by repeatedly sampling a task, performing stochastic gradient descent on it, and updating the initial parameters towards the final parameters learned on that task. Reptile is the application of the Shortest Descent algorithm to the meta-learning setting, and is mathematically similar to first-order MAML (which is a version of the well-known MAML algorithm) that only needs black-box access to an optimizer such as SGD or Adam, with similar co
We’re providing 6–10 stipends and mentorship to individuals from underrepresented groups to study deep learning full-time for 3 months and open-source a project.
AI 速览 Meta强化学习探索策略研究提出若干关键考量,聚焦任务分布与探索效率的权衡。
AI 速览 OpenAI发布多目标强化学习机器人环境基准,涵盖灵巧手操作等挑战性任务,并公开征集相关研究。
Come to OpenAI’s office in San Francisco’s Mission District for talks and a hackathon on Saturday, March 3rd.
We’re excited to welcome new donors to OpenAI.
We’ve designed a method that encourages AIs to teach each other with examples that also make sense to humans. Our approach automatically selects the most informative examples to teach a concept—for instance, the best images to describe the concept of dogs—and experimentally we found our approach to be effective at teaching both AIs
We’ve built a system for automatically figuring out which object is meant by a word by having a neural network decide if the word belongs to each of about 100 automatically-discovered “types” (non-exclusive categories).
We’re releasing a new batch of seven unsolved problems which have come up in the course of our research at OpenAI.
AI 速览 通过L₀正则化学习稀疏神经网络。
AI 速览 可解释与教学示例
Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.
AI 速览 Asymmetric actor critic方法被提出用于基于图像的机器人学习。