lasgroup/SDPO
**Brief Summary (2‑3 sentences)** lasgroup/SDPO implements Self‑Distillation for Reinforcement Learning (SDPO), letting developers add “smart” AI behavior to pr
Original source**Brief Summary (2‑3 sentences)** lasgroup/SDPO implements Self‑Distillation for Reinforcement Learning (SDPO), letting developers add “smart” AI behavior to pr
Original source