OpenAI Blog

Some considerations on learning to explore via meta-reinforcement learning

Ingredients for robotics research

We’re releasing eight simulated robotics environments and a Baselines implementation of Hindsight Experience Replay,…

Multi-Goal Reinforcement Learning: Challenging robotics environments and request for research

OpenAI hackathon

Come to OpenAI’s office in San Francisco’s Mission District for talks and a hackathon on Saturday, March 3rd.

OpenAI supporters

We’re excited to welcome new donors to OpenAI.

Preparing for malicious uses of AI

We’ve co-authored a paper that forecasts how malicious actors could misuse AI technology, and potential ways we can…

Interpretable machine learning through teaching

We’ve designed a method that encourages AIs to teach each other with examples that also make sense to humans. Our…

Discovering types for entity disambiguation

We’ve built a system for automatically figuring out which object is meant by a word by having a neural network decide…

Requests for Research 2.0

We’re releasing a new batch of seven unsolved problems which have come up in the course of our research at OpenAI.

Scaling Kubernetes to 2,500 nodes

Block-sparse GPU kernels

We’re releasing highly-optimized GPU kernels for an underexplored class of neural network architectures: networks with…

Learning sparse neural networks through L₀ regularization

Interpretable and pedagogical examples

Learning a hierarchy

We’ve developed a hierarchical reinforcement learning algorithm that learns high-level actions useful for solving a…

Generalizing from simulation

Our latest robotics techniques allow robot controllers, trained entirely in simulation and deployed on physical robots,…

Asymmetric actor critic for image-based robot learning

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

Domain randomization and generative models for robotic grasping

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…

Competitive self-play

We’ve found that self-play allows simulated AIs to discover physical skills like tackling, ducking, faking, kicking,…

Nonlinear computation in deep linear networks

Learning to model other minds

We’re releasing an algorithm which accounts for the fact that other agents are learning too, and discovers…

Learning with opponent-learning awareness

OpenAI Baselines: ACKTR & A2C

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

More on Dota 2

Our Dota 2 result shows that self-play can catapult the performance of machine learning systems from far below human…

Dota 2

We’ve created a bot which beats the world’s top professionals at 1v1 matches of Dota 2 under standard tournament rules.…

Gathering human feedback

RL-Teacher is an open-source implementation of our interface to train AIs via occasional human feedback rather than…

Better exploration with parameter noise

We’ve found that adding adaptive noise to the parameters of reinforcement learning algorithms frequently boosts…

Proximal Policy Optimization

We’re releasing a new class of reinforcement learning algorithms, Proximal Policy Optimization (PPO), which perform…

Robust adversarial inputs

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

Hindsight Experience Replay

Teacher–student curriculum learning

Faster physics in Python

We’re open-sourcing a high-performance Python library for robotic simulation using the MuJoCo engine, developed over…

Learning from human preferences

One step towards building safe AI systems is to remove the need for humans to write goal functions, since using a…

Learning to cooperate, compete, and communicate

Multiagent environments where agents compete for resources are stepping stones on the path to AGI. Multiagent…

UCB exploration via Q-ensembles