AI 뉴스

Faulty reward functions in the wild

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.

Universe

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.

OpenAI and Microsoft

We’re working with Microsoft to start running most of our large-scale experiments on Azure.

#Exploration: A study of count-based exploration for deep reinforcement learning

On the quantitative analysis of decoder-based generative models

A connection between generative adversarial networks, inverse reinforcement learning, and energy-based models

RL²: Fast reinforcement learning via slow reinforcement learning

Variational lossy autoencoder

Extensions and limitations of the neural GPU

Semi-supervised knowledge transfer for deep learning from private training data

Report from the self-organizing conference

Last week we hosted over a hundred and fifty AI practitioners in our offices for our first self-organizing conference on machine learning.

Transfer from simulation to real world through learning deep inverse dynamics model

Infrastructure for deep learning

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.

Machine Learning Unconference

The latest information about the Unconference is now available at the Unconference wiki, which will be periodically updated with more information for attendees.

Special projects

Impactful scientific work requires working on the right problems—problems which are not just interesting, but whose solutions matter.

Concrete AI safety problems

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 technical goals

OpenAI’s mission is to build safe AI, and ensure AI’s benefits are as widely and evenly distributed as possible.

Generative models

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 importan…

Adversarial training methods for semi-supervised text classification

OpenAI Gym Beta

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.