什么是Experience Replay和Seperate Target Networks

什么是Experience Replay, Seperate Target Network

  • 最近看到的一篇论文中提到的面对RL network不稳定甚至发散两个方法。

    • non-linear function approximator is unstable or even to diverge.

    • In RL, it's common to leverage a neural network as the function approximator.

  • 阅读Human-level control through deep reinforcement learning的笔记。

Experience Replay

Goals

  • 问题:
    • ML都假设数据是IID。
    • 但是RL连续online训练中,连续的samples有着很强的关联,所以可能导致network会陷入局部最小值。
  • 优点:
    • To smooth out learning, avoid oscillations or divergence in the parameters.
    • Randomizing the samples breaks these correlations and therefore reduces the variance of the updates.
    • Experience replay使训练任务更加像常见的监督学习了,可以简化调试、测试算法。

Method

  • 主要是用一个buffer存之前的experiences <s, a, r, s'>。
  • 每次从update的时候均匀地从Buffer中随机sample来用。
  • image-20211223150451105

Seperate Target Network

Goals and Strengths

  • To improve the stability of method.
  • Reduces oscillations or divergence of the policy.

Method

  • image-20211223150643783

  • 主要是每C次updates之后,就Clone Q网络作为target network Q',Q' 用于生成targets(假定的现实值)。

  • Target network是旧的参数network,prediction network是在更新的network。

  • 用旧的参数来生成targets给更新Q和update影响targets之间产生了一个delay,因此making divergence or oscillations much more unlikely.

算法

  • 使用experience replay and seperate target network.
  • image-20211223150742813

Reference

  • Human-level control through deep reinforcement learning
posted @ 2021-12-23 15:31  xxxuanei  阅读(103)  评论(0编辑  收藏  举报