Latest AI/ML News

We’ve created the world’s first Spam-detecting AI trained entirely in simulation and deployed on a physical robot.

We’ve developed an unsupervised system which learns an excellent representation of sentiment, despite being trained only to predict the next character…

We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.

We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new task after seeing it done once…

We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performance on par with published result…

Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent environments have two useful properties:…

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 goal, or…

We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over our past year of robotics researc…

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last…

We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform comparably or better than state-of…

We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method i…

RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than hand-crafted reward functions. The…

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 game from…

Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human level to superhuman, given suffic…

We’re releasing two new OpenAI Baselines implementations: ACKTR and A2C. A2C is a synchronous, deterministic variant of Asynchronous Advantage Actor C…