RESEARCH

Learning to model other minds

8 years ago
RESEARCH

OpenAI Baselines: ACKTR & A2C

8 years ago
RESEARCH

More on Dota 2

8 years ago
RESEARCH

Dota 2

8 years ago
RESEARCH

Gathering human feedback

8 years ago
RESEARCH

Better exploration with parameter noise

8 years ago
RESEARCH

Proximal Policy Optimization

8 years ago
OpenAI and Microsoft
OpenAI and Microsoft
9 years ago
Report from the self-organizing conference
Report from the self-organizing conference
9 years ago
Infrastructure for deep learning
Infrastructure for deep learning
9 years ago
OpenAI technical goals
OpenAI technical goals
9 years ago
Generative models
Generative models
9 years ago
Team update
Team update
9 years ago
OpenAI Gym Beta
OpenAI Gym Beta
9 years ago
Welcome, Pieter and Shivon!
Welcome, Pieter and Shivon!
9 years ago
Team++
Team++
10 years ago
Introducing OpenAI
Introducing OpenAI
10 years ago
COMPANY

Machine Learning Unconference
COMPANY

Team update

 COMPANY

Special projects

 SAFETY & ALIGNMENT

Concrete AI safety problems

Editor's pick

Spam detection in the physical world
RESEARCH

Spam detection in the physical world

9 years ago

Latest Briefs

Fast updates from the latest stories.

Robust adversarial inputs
RESEARCH
Robust adversarial inputs
8 years ago
Faster physics in Python
RESEARCH
Faster physics in Python
8 years ago
Learning from human preferences
SAFETY & ALIGNMENT
Learning from human preferences
8 years ago
Learning to cooperate, compete, and communicate
RESEARCH
Learning to cooperate, compete, and communicate
8 years ago
OpenAI Baselines: DQN
RESEARCH
OpenAI Baselines: DQN
8 years ago
Robots that learn
RESEARCH
Robots that learn
8 years ago
Roboschool
RESEARCH
Roboschool
8 years ago
Unsupervised sentiment neuron
RESEARCH
Unsupervised sentiment neuron
9 years ago

More Stories