data_mining:nyu_deep_learning_21:planning_and_control

Planning and control

  • Backprop through kinematic equation
  • Minimization wrt the latent

$\dot{x}=f(x,u)$

$u$ control (latent variable) $x$ state

$\frac{dx(t)}{dt} = f(x(t), u(t))$

temporal function $t$

  • data_mining/nyu_deep_learning_21/planning_and_control.txt
  • Last modified: 2021/07/08 21:10
  • by phreazer