zoukankan      html  css  js  c++  java
  • Deep RL Bootcamp Lecture 6: Nuts and Bolts of Deep RL Experimentation

     

     

     

    fast feedback to  robot with better shape reward func, and learning could be much faster

     

    open ai baseline 

    rllab

     

      

    multiple tasks and multiple seeds to test the robustness.

      

     don't believe only one trial's result, it could just be a fortunate trial, unless the imporvement is huge.

     

     

     

    KL = 0.1 is a small update

    KL = 10 is a large update

     

     

     

     

    DQN is not effective enough in many problems, especially on continuous control problem.

    But that doesn't mean it's a bad algorithm.

    So you shouldn't expect an algorithm solving everything without tunning, at least now.

    batch norm, dropout, or big networks? no, we try 2 layers with 64 units.

    at least now these techniques are not suitable for RL.

     if you don't care much about sample complexity,  PG are probably the way to go.

     qlearning is more implicit what is going in it , while PG is just gradient descent

     dqn and it relatives work well game like image as input, while policy based works better on continuous control tasks, like locomotion

     https://en.wikipedia.org/wiki/Sample_complexity

     

     I use randomly initialization of hyperparameters........

    audience laugh.... 

  • 相关阅读:
    学姐学长们的测试
    loli的测试——搜索
    搜索-2
    单调队列
    乱搞题 (不知道怎么分类)
    对拍及数据生成
    搜索-1
    矩形重叠
    拼写单词
    java笔记
  • 原文地址:https://www.cnblogs.com/ecoflex/p/8977582.html
Copyright © 2011-2022 走看看