def T(self, state, action):
if action is None:
return [(0.0, state)]
else:
return [(0.8, self.go(state, action)),
(0.1, self.go(state, turn_right(action))),
(0.1, self.go(state, turn_left(action)))]
def T(self, state, action):
if action is None:
return [(0.0, state)]
else:
return [(0.8, self.go(state, action)),
(0.1, self.go(state, turn_right(action))),
(0.1, self.go(state, turn_left(action)))]
def T(self, state, action):
if action is None:
return [(0.0, state)]
else:
# Updating to the transition matrix from the question2.
return [(0.7, self.go(state, action)),
(0.15, self.go(state, turn_right(action))),
(0.15, self.go(state, turn_left(action)))]
def T(self, state, action):
# print("state:{0},a:{1},ra:{2},la:{3}".format(state,action,turn_right(action),turn_left(action)))
if action is None:
#アクションが取られなかった時、そのまま。
return [(0.0, state)]
else:
# アクションが取られた時、
# 行きたい方向に0.8、その左右に0.1の確率で遷移する。
list1 = []
acts = [action, turn_right(action), turn_left(action)]
pros = [0.8, 0.1, 0.1]
for (a, p) in zip(acts, pros):
if self.state_check([x + y for (x, y) in zip(state, a)]):
list1.append((p, self.go(state, a)))
return list1