OpenAI Blog
OpenAI Blog
AI News & Updates
Stay ahead of
AI news
972+ articles from 7 top sources — updated every 2 hours.
OpenAI Blog
OpenAI Blog
Competitive self-play
We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving fo...
OpenAI Blog
OpenAI Blog
Meta-learning for wrestling
We show that for the task of simulated robot wrestling, a meta-learning agent can learn to quickly defeat a stronger non-meta-learning agent...
OpenAI Blog
OpenAI Blog
OpenAI Blog
OpenAI Blog
Learning to model other minds
We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative...
OpenAI Blog
OpenAI Blog
OpenAI Blog
OpenAI Blog
OpenAI Baselines: ACKTR & A2C
We’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advanta...
OpenAI Blog
OpenAI Blog
More on Dota 2
Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, gi...
OpenAI Blog
OpenAI Blog
Dota 2
We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules. The bot learned the ...
OpenAI Blog
OpenAI Blog
Gathering human feedback
RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward func...
OpenAI Blog
OpenAI Blog
Better exploration with parameter noise
We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploratio...
OpenAI Blog
OpenAI Blog
Proximal Policy Optimization
We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform comparably or better tha...
OpenAI Blog
OpenAI Blog
Robust adversarial inputs
We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim ...
OpenAI Blog
OpenAI Blog
OpenAI Blog
OpenAI Blog
OpenAI Blog
OpenAI Blog
Faster physics in Python
We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of roboti...
OpenAI Blog
OpenAI Blog
Learning from human preferences
One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a simple proxy for a complex...
OpenAI Blog
OpenAI Blog
Learning to cooperate, compete, and communicate
Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent environments have two useful p...
OpenAI Blog
OpenAI Blog
OpenAI Blog
OpenAI Blog
OpenAI Baselines: DQN
We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performance on par with publis...