Adversarial attacks on neural network policies
Explorar
Noticias de IA
30239 elementos — filtrados, clasificados y sin duplicados
Team update
PixelCNN++: Improving the PixelCNN with discretized logistic mixture likelihood and other…
Faulty reward functions in the wild
Universe
OpenAI and Microsoft
#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…
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
Transfer from simulation to real world through learning deep inverse dynamics model
Infrastructure for deep learning
Machine Learning Unconference
Team update
Special projects
Concrete AI safety problems
OpenAI technical goals
Generative models
Team update
Adversarial training methods for semi-supervised text classification
OpenAI Gym Beta
Welcome, Pieter and Shivon!
Team++
Weight normalization: A simple reparameterization to accelerate training of deep neural n…
Introducing OpenAI