Open Models Almanac
Methodspost-trainingrollout & RL infrastructure

single mention · post-training

Asynchronous Agent Reinforcement Learning algorithms

The evidence names asynchronous Agent RL algorithms but does not specify their algorithmic mechanism.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See rollout & RL infrastructure for the methods filed beside it.

Also called asynchronous Agent RL algorithms.

Filed under post-training › rollout & RL infrastructure