Cooperative Behaviours with Swarm Intelligence in Multirobot Systems for Safety Inspections in Underground Terrains

Algorithm 1

Q-learning algorithm.

Steps:

initialize 𝑄(𝑠,𝑎) arbitrarily

repeat (for each episode):

     initialize 𝑠

     Repeat (for each step of episode):

      Choose 𝑎 from s using policy derived from 𝑄

      Take action 𝑎, observe 𝑠,𝑠^′

       𝑄(𝑠,𝑎)←𝑄(𝑠,𝑎)+𝛼𝑟+𝛾max_𝑎′𝑄𝑠^′,𝑎^′−𝑄(𝑠,𝑎)

      𝑠←𝑠^′

      until s is terminal