Skip to content
AIMarketCap

RL-Teacher

Product
OpenAIarchived

Open-source implementation for training agents from human preference feedback.

Launched
Aug 3, 2017
Models
—
Modality
—
Open source
Yes
API available
—
Releases
2

Releases

2
Aug 3, 2017RL-Teacher code releasedRL-Teacher

OpenAI released code for training reinforcement-learning agents from human feedback.

OpenAI SDK releaseOpenAIRL-Teacher
Jun 13, 2017Learning from human preferences research publishedRL-Teacher

OpenAI and DeepMind researchers showed how agents can learn complex behavior from human preference comparisons.

OpenAI Research paperOpenAIRL-Teacher