974+ articles from 7 top sources — updated every 2 hours.
We’ve designed a method that encourages AIs to teach each other with examples that also make sense to humans. Our approach automatically sel...
We’ve built a system for automatically figuring out which object is meant by a word by having a neural network decide if the word belongs to...
We’re releasing a new batch of seven unsolved problems which have come up in the course of our research at OpenAI....
We’re releasing highly-optimized GPU kernels for an underexplored class of neural network architectures: networks with block-sparse weights....
We’ve developed a hierarchical reinforcement learning algorithm that learns high-level actions useful for solving a range of tasks, allowing...
Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanne...
We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving fo...
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...
We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative...
We’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advanta...
Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, gi...
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 ...