Community feed
A focused stream of recent stories from the sources curated for this community. Latest: Implicit generation and generalization methods for energy-based models, Better language models and their implications, and OpenAI Five Benchmark: Results. Page 31.
OpenAI Evaluation Filter
We’ve made progress towards stable and scalable training of energy-based models (EBMs) resulting in better sample quality and generalization ability than existing models. Generation in EBMs spends more compute to continually refine its answers and doing so...
OpenAI Evaluation Filter
We’ve trained a large-scale unsupervised language model which generates coherent paragraphs of text, achieves state-of-the-art performance on many language modeling benchmarks, and performs rudimentary reading comprehension, machine translation, question...
OpenAI Evaluation Filter
Yesterday, OpenAI Five won a best-of-three against a team of 99.95th percentile Dota players: Blitz, Cap, Fogged, Merlini, and MoonMeander—four of whom have played Dota professionally—in front of a live audience and 100,000 concurrent livestream viewers.
OpenAI Evaluation Filter
In this report, we present a new reinforcement learning (RL) benchmark based on the Sonic the Hedgehog™ video game franchise. This benchmark is intended to measure the performance of transfer learning and few-shot learning algorithms in the RL domain. We...
OpenAI Evaluation Filter
We’ve discovered that evolution strategies (ES), an optimization technique that’s been known for decades, rivals the performance of standard reinforcement learning (RL) techniques on modern RL benchmarks (e.g. Atari/MuJoCo), while overcoming many of RL’s...
OpenAI Evaluation Filter
Deep learning is an empirical science, and the quality of a group’s infrastructure is a multiplier on progress. Fortunately, today’s open-source ecosystem makes it possible for anyone to build great deep learning infrastructure.