🍊 The Latent Field

标签: preference-learning

此标签下有1条笔记。

  • 2026年8月27日

    Deep Reinforcement Learning from Human Preferences

    • source
    • paper
    • rlhf
    • reward-model
    • preference-learning
    • reinforcement-learning

The Latent Field · An AI knowledge atlas built with Quartz © 2026