zoukankan      html  css  js  c++  java
  • Deep RL Bootcamp Frontiers Lecture I: Recent Advances,

    high bias

    if the robot has learnt something (no changes appear with iterations)

    however, in the real world tasks, the task could change a little bit, then the robot will failed to generalize.

     no matter how well we train the robot in situations, there's always something that happens and messes up the system.

     

     

     

     

    14 robot, sharing their own experience to each other

      

     

    here the goal is to grasp anything. no task here

     

     

     

    a few clips of our best trained neural network, picking up four objects that are visually kind of similar. They are all blue and roughly the same size, roughly rectangular.

     

     

     

     

     

     

      

     

     

     

     

     

     

     

     

     

      

     

     

     

     imitation learning

     

     

     

     

    push the green tedy bear to the red spot

     

     

     



     

     

    终于结束了,接下来需要

    1,学习使用tensorflow和pytorch

    2,对CNN、RNN、GAN动手实践,做项目

    (大概需要20天)

    3,学习基础的ML(大概需要4天)

    4,学习raspberry pi和arduino(大概需要4天)

  • 相关阅读:
    XML语法
    C/C++对MySQL操作
    HDU 3966 Aragorn's Story
    SPOJ 375 Query on a tree
    SPOJ 913 Query on a tree II
    SPOJ 6779 Can you answer these queries VII
    URAL 1471 Tree
    SPOJ 2798 Query on a tree again!
    POJ 3237 Tree
    SPOJ 4487 Can you answer these queries VI
  • 原文地址:https://www.cnblogs.com/ecoflex/p/8991605.html
Copyright © 2011-2022 走看看