Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

Concatenated routing replay

Concatenates expert-routing records from rollout segments spanning multiple checkpoints instead of discarding and recomputing them.

The sources on this page only mention it in passing. The line above is the extraction's one-line gloss. See reinforcement learning algorithm for the methods filed beside it.

Filed under post-training › reinforcement learning algorithm