crawler.py 文件源码

def doAction(self, action):
        """
          Perform the action and update
          the current state of the Environment
          and return the reward for the
          current state, the next state
          and the taken action.

          Returns:
            nextState, reward
        """
        nextState, reward =  None, None

        oldX,oldY = self.crawlingRobot.getRobotPosition()

        armBucket,handBucket = self.state
        armAngle,handAngle = self.crawlingRobot.getAngles()
        if action == 'arm-up':
            newArmAngle = self.armBuckets[armBucket+1]
            self.crawlingRobot.moveArm(newArmAngle)
            nextState = (armBucket+1,handBucket)
        if action == 'arm-down':
            newArmAngle = self.armBuckets[armBucket-1]
            self.crawlingRobot.moveArm(newArmAngle)
            nextState = (armBucket-1,handBucket)
        if action == 'hand-up':
            newHandAngle = self.handBuckets[handBucket+1]
            self.crawlingRobot.moveHand(newHandAngle)
            nextState = (armBucket,handBucket+1)
        if action == 'hand-down':
            newHandAngle = self.handBuckets[handBucket-1]
            self.crawlingRobot.moveHand(newHandAngle)
            nextState = (armBucket,handBucket-1)

        newX,newY = self.crawlingRobot.getRobotPosition()

        # a simple reward function
        reward = newX - oldX

        self.state = nextState
        return nextState, reward