ScholarGate
Asistente

Comparar métodos

Revisa los métodos seleccionados uno junto a otro; las filas que difieren aparecen resaltadas.

Aprendizaje por Refuerzo Ajustado×Aprendizaje por Refuerzo Auto-supervisado×
CampoAprendizaje profundoAprendizaje profundo
FamiliaMachine learningMachine learning
Año de origen2017–20222020
Autor originalChristiano, P. et al.; Ouyang, L. et al.Laskin, M.; Srinivas, A.; Abbeel, P. (and contemporaries)
TipoPolicy adaptation via fine-tuningSelf-supervised auxiliary-task learning for RL
Fuente seminalOuyang, 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 ↗Laskin, M., Srinivas, A., & Abbeel, P. (2020). CURL: Contrastive Unsupervised Representations for Reinforcement Learning. Proceedings of the 37th International Conference on Machine Learning (ICML), PMLR 119, 5639–5650. link ↗
AliasRL fine-tuning, policy fine-tuning, RLHF, reinforcement learning from human feedbackSSL-RL, self-supervised RL, representation-based reinforcement learning, auxiliary-task RL
Relacionados54
ResumenFine-Tuned Reinforcement Learning adapts a pre-trained policy or model to a new task or behavioral objective using reinforcement signals — including human feedback — rather than retraining from scratch. Popularized by RLHF, it is the core technique behind aligning large language models and adapting deep RL agents to specialized environments with minimal additional data.Self-supervised Reinforcement Learning (SSL-RL) augments standard RL training with self-supervised auxiliary objectives — such as contrastive, predictive, or data-augmentation-based tasks — applied to the agent's own experience. These objectives improve the quality of learned representations without requiring extra human labels, enabling faster convergence and better sample efficiency, especially in high-dimensional observation spaces like raw pixels.
ScholarGateConjunto de datos
  1. v1
  2. 2 Fuentes
  3. PUBLISHED
  1. v1
  2. 2 Fuentes
  3. PUBLISHED

Ir a la búsqueda Descargar diapositivas

ScholarGateComparar métodos: Fine-Tuned Reinforcement Learning · Self-supervised Reinforcement Learning. Recuperado el 2026-06-17 de https://scholargate.app/es/compare