用RLHF训练一个chatGPT在chatGPT预训练模型上,使用RLHF 训练chatGPT,使它能够按照设计者要求形成某种偏好

语言处理路径
使用RLHF训练一个chatGPT在chatGPT预训练模型上,使用
RLHF (Reinforcement Learning from Human Feedback)
训练chatGPT,使它能够按照设计者要求形成某种偏好
(求帮忙给做一个)

不知道你这个问题是否已经解决, 如果还没有解决的话:
  • 文章:ChatGPT 中的人类反馈强化学习 (RLHF) 实战 中也许有你想要的答案,请看下吧
  • 除此之外, 这篇博客: 关于 ChatGPT 必看的 10 篇论文中的 5 RLHF 部分也许能够解决你的问题, 你可以仔细阅读以下内容或者直接跳转源博客中阅读:

    InstructGPT/GPT3.5(ChatGPT的前身)与 GPT-3 的主要区别在于,新加入了被称为 RLHF(Reinforcement Learning from Human Feedback,人类反馈强化学习)。这一训练范式增强了人类对模型输出结果的调节,并且对结果进行了更具理解性的排序。

    • Title:
    Augmenting Reinforcement Learning with Human Feedback
  • Abstract:As computational agents are increasingly used beyond research labs, their success will depend on their ability to learn new skills and adapt to their dynamic, complex environments. If human users — without programming skills — can transfer their task knowledge to agents, learning can accelerate dramatically, reducing costly trials. The TAMER framework guides the design of agents whose behavior can be shaped through signals of approval and disapproval, a natural form of human feedback. More recently, TAMER+RL was introduced to enable human feedback to augment a traditional reinforcement learning (RL) agent that learns from a Markov decision process’s (MDP) reward signal. Using a reimplementation of TAMER and TAMER+RL, we address limitations of prior work, contributing in two critical directions. First, the four successful techniques for combining a human reinforcement with RL from prior TAMER+RL work are tested on a second task, and these techniques’ sensitivities to parameter changes are analyzed. Together, these examinations yield more general and prescriptive conclusions to guide others who wish to incorporate human knowledge into an RL algorithm. Second, TAMER+RL has thus far been limited to a sequential setting, in which training occurs before learning from MDP reward. We modify the sequential algorithms to learn simultaneously from both sources, enabling the human feedback to come at any time during the reinforcement learning process. To enable simultaneous learning, we introduce a new technique that appropriately determines the magnitude of the human model’s influence on the RL algorithm throughout time and state-action space.
  • 摘要:随着计算代理越来越多地被用于研究实验室之外,它们的成功将取决于它们学习新技能和适应其动态、复杂环境的能力。如果人类用户–没有编程技能–能够将他们的任务知识转移给代理,那么学习就会大大加快,减少昂贵的试验。TAMER框架指导代理人的设计,其行为可以通过批准和不批准的信号来塑造,这是人类反馈的一种自然形式。最近,TAMER+RL被引入,使人类反馈能够增强传统的强化学习(RL)代理,该代理从马尔科夫决策过程(MDP)的奖励信号中学习。通过对TAMER和TAMER+RL的重新实现,我们解决了先前工作的局限性,在两个关键方向上做出了贡献。首先,我们在第二个任务上测试了先前TAMER+RL工作中结合人类强化和RL的四种成功技术,并分析了这些技术对参数变化的敏感性。这些检查共同产生了更多的一般性和规范性的结论,以指导那些希望将人类知识纳入RL算法的其他人。第二,TAMER+RL到目前为止仅限于顺序设置,即在从MDP奖励中学习之前发生训练。我们对顺序算法进行了修改,使其能够同时从两个来源进行学习,从而使人类的反馈能够在强化学习过程中的任何时候出现。为了实现同步学习,我们引入了一种新的技术,适当地确定人类模型在整个时间和状态动作空间对RL算法的影响程度。

如果你已经解决了该问题, 非常希望你能够分享一下解决方案, 写成博客, 将相关链接放在评论区, 以帮助更多的人 ^-^