Evolved Policy Gradients
OpenAI Blog
April 18, 2018
We’re releasing an experimental metalearning approach called Evolved Policy Gradients, a method that evolves the loss function of learning agents, which can enable fast training on novel tasks. Agents trained with EPG can succeed at basic tasks at test time that were outside their training regime, like learning to navigate to an object on a different side of the room from where it was placed during training.
Verticals
airesearch
Originally published on OpenAI Blog on 4/18/2018