A Dynamic Hidden Forwarding Path Planning Method Based on Improved Q-Learning in SDN Environments

Algorithm 1

Planning optimal attack path based on improved Q-learning algorithm.

Require:

Host weight

The attack success rate of vulnerability

Vulnerability

Host Name

Ensure: Optimal policy (attack path)

  function IQL(, , , )

   obtain the number of vulnerabilities

   obtain the number of hosts

  getstate gain state set

  getNumber initialize discount factor

   initialize value matrix

   build reward matrix

  for     is iteration step do  

obtain the optimal policy

  if     then break

  end if

  end for  

  return  

  end function