def reward(self, state, action):
if state == 0:
return 0.0
else:
return -1.0
def get_actions(self, state):
return [i for i in range(self.action_size)]
def print_evaluation(self):
print("value matrix")
for i in range(4):
for j in range(4):
state_idx = (i*4+j) % 15
print("{:.3f}".format(self.v[state_idx]), end=' ')
print()
def print_improvement(self):
print("policy matrix")
for i in range(4):
for j in range(4):
state_idx = (i*4+j) % 15
print(self.p[state_idx], end=' ')
print()
if __name__ == "__main__":
test = myAgent(15, 4, 1.0)
method = DP.algo(test, threshold=0.0001)
method.policy_evaluation(show=True)
# method.policy_iteration(show=True)
# method.value_iteration(show=True)
num1 = state // 21
num2 = state % 21
actions = []
for a in range(self.action_size):
moved = a - 5
if num1 + moved < 0 or num2 - moved < 0: continue
actions.append(a)
return actions
def print_evaluation(self):
print("value matrix")
for i in range(21):
for j in range(21):
state_idx = (i * 21 + j)
print("{:.3f}".format(self.v[state_idx]), end=' ')
print()
def print_improvement(self):
print("policy matrix")
for i in range(21):
for j in range(21):
state_idx = (i * 21 + j)
print(self.p[state_idx], end=' ')
print()
if __name__ == "__main__":
agent = Agent(21 * 21, 11, 0.9)
method = DP.algo(agent, 0.0001)
method.policy_iteration() #show=True)