Multiagent Cooperative Learning Strategies for Pursuit-Evasion Games

Algorithm 5

RL-Fusing algorithm.

Require: A set of strategies, an initial state

(1)  ←

(2) while true do

(3)   if   is coordinated state then

(4)        ←

(5)      if    then

(6)       select a strategy randomly //the same for all agent

(7)      else

(8)       rank strategies

(9)       communicate ranks

(10)          receive ranks from other agents

(11)           average ranks

(12)          select corresponding strategy

(13)       end if

(14)       execute selected strategy

(15)       receive reward

(16)       transit to a new state

(17)       update -value

(18)    else

(19)       act with a predefined or random policy

(20)    end if

(21) end while