RSS: OpenAI News
We’ve designed a method that encourages AIs to teach each other with examples that also make sense to humans. Our approach automatically selects the most informative examples to teach a concept—fo...
RSS: OpenAI News
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 each of about 100 automatically-discovered “types” (n...
RSS: OpenAI News
We’re releasing a new batch of seven unsolved problems which have come up in the course of our research at OpenAI.
RSS: OpenAI News
RSS: OpenAI News
We’re releasing highly-optimized GPU kernels for an underexplored class of neural network architectures: networks with block-sparse weights. Depending on the chosen sparsity, these kernels can run o...
RSS: OpenAI News
RSS: OpenAI News
RSS: OpenAI News
We’ve developed a hierarchical reinforcement learning algorithm that learns high-level actions useful for solving a range of tasks, allowing fast solving of tasks requiring thousands of timesteps. O...
RSS: OpenAI News
Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots, to react to unplanned changes in the environment as they solve simple tasks. Tha...
RSS: OpenAI News
RSS: OpenAI News
RSS: OpenAI News
RSS: OpenAI News
We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking, catching, and diving for the ball, without explicitly designing an environment wi...
RSS: OpenAI News
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, and also show that the meta-learning agent can adapt to ph...
RSS: OpenAI News
RSS: OpenAI News
We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers self-interested yet collaborative strategies like tit-for-tat in the iterated prisoner’s ...
RSS: OpenAI News
RSS: OpenAI News
We’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advantage Actor Critic (A3C) which we’ve found gives equal perf...
RSS: OpenAI News
Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given sufficient compute. In the span of a month, our system w...