API
Research
Blog
About
Blog
John Schulman
2022
Our approach to alignment research
August 24, 2022
—
Research
2021
WebGPT: Improving the Factual Accuracy of Language Models through Web Browsing
December 16, 2021
—
Research
2021
Solving Math Word Problems
October 29, 2021
—
Research
2019
Procgen Benchmark
December 3, 2019
—
Research
2018
Retro Contest: Results
June 22, 2018
—
Research
2018
OpenAI Fellows Fall 2018
May 30, 2018
—
Announcements
,
Fellows
2018
Gym Retro
May 25, 2018
—
Research
2018
Retro Contest
April 5, 2018
—
Research
,
Milestones
2018
Reptile: A Scalable Meta-Learning Algorithm
March 7, 2018
—
Research
2018
Requests for Research 2.0
January 31, 2018
—
Research
2017
Learning a Hierarchy
October 26, 2017
—
Research
2017
OpenAI Baselines: ACKTR & A2C
August 18, 2017
—
Research
,
Milestones
,
OpenAI Baselines
2017
Proximal Policy Optimization
July 20, 2017
—
Research
,
Milestones
2017
OpenAI Baselines: DQN
May 24, 2017
—
Research
,
Milestones
,
OpenAI Baselines
2017
Roboschool
May 15, 2017
—
Research
2017
Evolution Strategies as a Scalable Alternative to Reinforcement Learning
March 24, 2017
—
Research
,
Milestones
2016
Generative Models
June 16, 2016
—
Research
,
Milestones
2016
OpenAI Gym Beta
April 27, 2016
—
Research