INNER CODE UNIT · Python
__init__
rlcode/reinforcement-learning · 1-grid-world/1-policy_iteration.py:7
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)]
# list of random policy (same probability of up, down, left, right)
self.policy_table = [[[0.25, 0.25, 0.25, 0.25]] * env.width
for _ in range(env.height)]
# setting terminal state
self.policy_table[2][2] = []
self.discount_factor = 0.9
def policy_evaluation(self):
next_value_table = [[0.00] * self.env.width
for _ in range(self.env.height)]
# Bellman Expectation Equation for the every states
for state in self.env.get_all_states():
value = 0.0