Open Models Almanac
Methodspost-trainingreinforcement learning algorithm

single mention · post-training

PPO-style policy-ratio clipping

Clips the policy ratio around a proximal policy.

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.

Also called PPO-style clipping.

Filed under post-training › reinforcement learning algorithm