Skip to main content
Join Community

Search AI Workflow Pro

Search tools, categories, stacks, and pages

Fresh daily

AI News

Latest AI tool releases, research breakthroughs, and industry news.

AllReleasesResearchFundingTutorialsOpinion

Older

Learning sparse neural networks through L₀ regularization

OpenAI Blog·Dec 4research

Interpretable and pedagogical examples

OpenAI Blog·Nov 2research

Learning a hierarchy

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. Our algorithm, when applied to a set of navigation problems, discovers a set of high-level actions for walking and crawling in different directions, which enables the agent to master new navigation tasks quickly.

OpenAI Blog·Oct 26research

Generalizing from simulation

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. That is, we’ve used these techniques to build closed-loop systems rather than open-loop ones as before.

OpenAI Blog·Oct 19research

Sim-to-real transfer of robotic control with dynamics randomization

OpenAI Blog·Oct 18research

Asymmetric actor critic for image-based robot learning

OpenAI Blog·Oct 18research

Domain randomization and generative models for robotic grasping

OpenAI Blog·Oct 17research

Meta-learning for wrestling

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 physical malfunction.

OpenAI Blog·Oct 11research

Competitive self-play

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 with these skills in mind. Self-play ensures that the environment is always the right difficulty for an AI to improve. Taken alongside our Dota 2 self-play results, we have increasing confidence that self-play will be a core part of powerful AI systems in the future.

OpenAI Blog·Oct 11research

Nonlinear computation in deep linear networks

OpenAI Blog·Sep 29research

Learning to model other minds

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 dilemma. This algorithm, Learning with Opponent-Learning Awareness (LOLA), is a small step towards agents that model other minds.

OpenAI Blog·Sep 14research

Learning with opponent-learning awareness

OpenAI Blog·Sep 13research

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.

OpenAI Blog·Aug 18release

More on Dota 2

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 went from barely matching a high-ranked player to beating the top pros and has continued to improve since then. Supervised deep learning systems can only be as good as their training datasets, but in self-play systems, the available data improves automatically as the agent gets better.

OpenAI Blog·Aug 16research

Dota 2

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 scratch by self-play, and does not use imitation learning or tree search. This is a step towards building AI systems which accomplish well-defined goals in messy, complicated situations involving real humans.

OpenAI Blog·Aug 11research

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.

OpenAI Blog·Aug 3release

Better exploration with parameter noise

We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts performance. This exploration method is simple to implement and very rarely decreases performance, so it’s worth trying on any problem.

OpenAI Blog·Jul 27research

Proximal Policy Optimization

We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform comparably or better than state-of-the-art approaches while being much simpler to implement and tune. PPO has become the default reinforcement learning algorithm at OpenAI because of its ease of use and good performance.

OpenAI Blog·Jul 20research

Robust adversarial inputs

We’ve created images that reliably fool neural network classifiers when viewed from varied scales and perspectives. This challenges a claim from last week that self-driving cars would be hard to trick maliciously since they capture images from multiple scales, angles, perspectives, and the like.

OpenAI Blog·Jul 17research

Hindsight Experience Replay

OpenAI Blog·Jul 5research