INNER CODE UNIT · Python

get_policy

rlcode/reinforcement-learning · 1-grid-world/1-policy_iteration.py:90

    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)

if __name__ == "__main__":
    env = Env()
    policy_iteration = PolicyIteration(env)
    display = GraphicDisplay(policy_iteration, title="Policy Iteration")

    def on_evaluate():
        policy_iteration.policy_evaluation()
        display.show_values(policy_iteration.value_table)

    def on_improve():

View source record →