RPT

Software / App

A related paper and technique for Reinforcement Pretraining, compared against RLP, which uses an external verifier and a sparse reward.

Mentioned in 1 video

Videos Mentioning RPT

Stanford CS25: Transformers United V6 I From Next-Token Prediction to Next-Generation Intelligence

Stanford CS25: Transformers United V6 I From Next-Token Prediction to Next-Generation Intelligence

Stanford Online

A related paper and technique for Reinforcement Pretraining, compared against RLP, which uses an external verifier and a sparse reward.