Technology News, Trends, And Future-Ready Signals

Robust adversarial inputs

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

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 our...

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 simple...

Learning to cooperate, compete, and communicate

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

UCB exploration via Q-ensembles

OpenAI Baselines: DQN

We’re open-sourcing OpenAI Baselines, our internal effort to reproduce reinforcement learning algorithms with performanc...

Robots that learn

We’ve created a robotics system, trained entirely in simulation and deployed on a physical robot, which can learn a new...

Roboschool

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

Equivalence between policy gradients and soft Q-learning

Stochastic Neural Networks for hierarchical reinforcement learning