INNER CODE UNIT · Python

__init__

rlcode/reinforcement-learning · 1-grid-world/2-value_iteration.py:5

    def __init__(self, env):
        self.env = env
        # 2-d list for the value function
        self.value_table = [[0.0] * env.width for _ in range(env.height)]
        self.discount_factor = 0.9

    # get next value function table from the current value function table
    def value_iteration(self):
        next_value_table = [[0.0] * self.env.width
                                    for _ in range(self.env.height)]
        for state in self.env.get_all_states():
            if state == [2, 2]:
                next_value_table[state[0]][state[1]] = 0.0
                continue
            value_list = []

            for action in self.env.possible_actions:
                next_state = self.env.state_after_action(state, action)

View source record →