Environment Class

#!/usr/bin/python2.7

class RoomEnv(Environment):
    # number of action values acceptable by the environment
    # Two events: go forward and go back through the door (but, how we know what room is connect to another?)
    indim = 2
    # Maybe a matrix where 0 is no connection and 1 is a connection(?)
                #    A,B,C,D,E,F
    #indim = array([[0,0,0,0,0,0],  # A
            [0,0,0,0,0,1],  # B
            [0,0,0,0,0,0],  # C
            [0,0,0,0,0,0],  # D
            [0,0,0,0,0,1],  # E
            [0,0,0,0,0,1],  # F
              ])

    # the number of sensors is the number of the rooms
    outdim = 6

    def getSensors(self):
        # Initial state:
        return start=array(2,2)

    def performAction(self, action):
        # We should look at all the states possible to learn what are the best option to go to the outside state.
        # Maybe a for loop that goes through all the paths and use some weight to know where is the best option?

        print "Action performed: ", action

    def reset(self):
            """ Most environments will implement this optional method that allows for reinitialization.
            """