Fresh daily
AI News
Latest AI tool releases, research breakthroughs, and industry news.
Older
Block-sparse GPU kernels
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 orders of magnitude faster than cuBLAS or cuSPARSE. We’ve used them to attain state-of-the-art results in text sentiment analysis and generative modeling of text and images.
OpenAI Baselines: ACKTR & A2C
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 performance. ACKTR is a more sample-efficient reinforcement learning algorithm than TRPO and A2C, and requires only slightly more computation than A2C per update.
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 functions. The underlying technique was developed as a step towards safe AI systems, but also applies to reinforcement learning problems with rewards that are hard to specify.
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 robotics research.
OpenAI Baselines: DQN
We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performance on par with published results. We’ll release the algorithms over upcoming months; today’s release includes DQN and three of its variants.
Roboschool
We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.
Distill
We’re excited to support today’s launch of Distill, a new kind of journal aimed at excellent communication of machine learning results (novel or existing).
Universe
We’re releasing Universe, a software platform for measuring and training an AI’s general intelligence across the world’s supply of games, websites and other applications.
Team update
We’ve hired more great people to help us achieve our goals. Welcome, everyone!
Team update
We’d like to welcome the latest set of team members to OpenAI (and we’re still hiring!)
OpenAI Gym Beta
We’re releasing the public beta of OpenAI Gym, a toolkit for developing and comparing reinforcement learning (RL) algorithms. It consists of a growing suite of environments (from simulated robots to Atari games), and a site for comparing and reproducing results.
Welcome, Pieter and Shivon!
We have two more team updates.
Team++
We've had some fantastic people join over the past few months (and we're still hiring). Welcome, everyone!