ScholarGate
Assistent
Machine learningDeep learning / NLP / CV

Finjusteret forstærkningslæring

Finjusteret forstærkningslæring (Fine-Tuned Reinforcement Learning) tilpasser en forudtrænet politik eller model til en ny opgave eller adfærdsmæssigt mål ved hjælp af forstærkningssignaler – herunder menneskelig feedback – snarere end at genoptræne fra bunden. Populariseret af RLHF, er det den centrale teknik bag at tilpasse store sprogmodeller og tilpasse dybe RL-agenter til specialiserede miljøer med minimal yderligere data.

Åbn i MethodMindSnartVideoSnartDownload slides

Læs hele metoden

Kun for medlemmer

Log ind med en gratis konto for at læse dette afsnit.

Log ind

Method map

The neighbourhood of related methods — select a node to explore.

Kilder

  1. Ouyang, L., Wu, J., Jiang, X., Almeida, D., Wainwright, C., Mishkin, P., Zhang, C., Agarwal, S., Slama, K., Ray, A., Schulman, J., Hilton, J., Kelton, F., Miller, L., Simens, M., Askell, A., Welinder, P., Christiano, P., Leike, J., & Lowe, R. (2022). Training language models to follow instructions with human feedback. Advances in Neural Information Processing Systems, 35, 27730–27744. link
  2. Christiano, P., Leike, J., Brown, T. B., Martic, M., Legg, S., & Amodei, D. (2017). Deep reinforcement learning from human preferences. Advances in Neural Information Processing Systems, 30. link

Sådan citerer du denne side

ScholarGate. (2026, June 3). Fine-Tuned Reinforcement Learning (Policy Adaptation via Fine-Tuning). ScholarGate. https://scholargate.app/da/deep-learning/fine-tuned-reinforcement-learning

Which method?

Set this method beside its closest kin and read them side by side — the library lays the books on the table; the choice is yours.

Compare side by side

Refereret af

ScholarGateFine-Tuned Reinforcement Learning (Fine-Tuned Reinforcement Learning (Policy Adaptation via Fine-Tuning)). Hentet 2026-06-15 fra https://scholargate.app/da/deep-learning/fine-tuned-reinforcement-learning · Datasæt: https://doi.org/10.5281/zenodo.20539026