INNER CODE UNIT · Python

random_pick

rlcode/reinforcement-learning · 1-grid-world/1-policy_iteration.py:79

        random_pick = random.randrange(100) / 100

        policy = self.get_policy(state)
        policy_sum = 0.0
        # return the action in the index
        for index, value in enumerate(policy):
            policy_sum += value
            if random_pick < policy_sum:
                return index

    # get policy of specific state
    def get_policy(self, state):
        if state == [2, 2]:
            return 0.0
        return self.policy_table[state[0]][state[1]]

    def get_value(self, state):
        return round(self.value_table[state[0]][state[1]], 2)

View source record →