The Next Input updates
Browse every published The Next Input update in a calm card overview with images, dates, and direct access to each article.
The Next Input update
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.
The Next Input update
Learning from human preferences
Read paper(opens in a new window)
The Next Input update
Learning to cooperate, compete, and communicate
View code(opens in a new window)Read paper(opens in a new window)
The Next Input update
UCB exploration via Q-ensembles
The Next Input update
OpenAI Baselines: DQN
View code(opens in a new window)
The Next Input update
Robots that learn
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.
The Next Input update
Roboschool
We are releasing Roboschool: open-source software for robot simulation, integrated with OpenAI Gym.
The Next Input update
Equivalence between policy gradients and soft Q-learning
The Next Input update
Stochastic Neural Networks for hierarchical reinforcement learning
Read paper(opens in a new window)
The Next Input update
Unsupervised sentiment neuron
We’ve developed an unsupervised system which learns an excellent representation of sentiment, despite being trained only to predict the next character in the text of Amazon reviews.
The Next Input update
Spam detection in the physical world
We’ve created the world’s first Spam-detecting AI trained entirely in simulation and deployed on a physical robot.
The Next Input update
Evolution strategies as a scalable alternative to reinforcement learning
Read paper(opens in a new window)Read documentation(opens in a new window)
Showing 1033 to 1044 of 1,127 updates.