Open Models Almanac
Methodspost-trainingreward modelling

single mention · post-training

Trajectory-quality reward

Combines imitation, collision, and jerk-related terms to score predicted trajectories.

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

Also called low-level trajectory quality reward.

Filed under post-training › reward modelling