OpenAI hackathon
8 years ago
Preparing for malicious uses of AI
8 years ago
OpenAI supporters
8 years ago
Learning a hierarchy
8 years ago
Generalizing from simulation
8 years ago
Meta-learning for wrestling
8 years ago
Competitive self-play
8 years ago
Learning to model other minds
8 years ago
OpenAI Baselines: ACKTR & A2C
8 years ago
More on Dota 2
8 years ago
Dota 2
8 years ago
Gathering human feedback
8 years ago
Editor's pick
RESEARCH
AI and compute
7 years ago
Latest Briefs
Fast updates from the latest stories.
COMPANY
OpenAI Five Benchmark
7 years ago
RESEARCH
Glow: Better reversible generative models
7 years ago
RESEARCH
Learning Montezuma’s Revenge from a single demonstration
7 years ago
RESEARCH
OpenAI Five
7 years ago
More Stories
RESEARCH
RESEARCH
RESEARCH
SAFETY & ALIGNMENT
RESEARCH
RESEARCH