EAQR: A Multiagent Q-Learning Algorithm for Coordination of Multiple Agents

Algorithm 1

EAQR for repeated games.

1: for each agent i, do

2: initialize with a number within (0,1) for ,

3: initialize with a number within (0,1)

4: : frequency of getting the maximum global immediate reward after selecting action

5: : number of sample games played

6: repeat for each game

7:  select an action with the probability of

8:  

9: execute action , update information about reward

10:  if then

11:   for each action do

12:    evaluate according to (4)

13:    

14:   end for each action

15:   

16:  end if

17: until the predefined number of games have been played

18: end for each agent

19: return Q-value function for each agent