def calculate_T(self, state, action):
if action:
return [(0.8, self.go(state, action)),
(0.1, self.go(state, turn_right(action))),
(0.1, self.go(state, turn_left(action)))]
else:
return [(0.0, state)]
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 interpret(self, action):
#Direction: 0 = straight, 1 = left, 2 = right
if action == 1:
return turn_left(self.direction)
elif action == 2:
return turn_right(self.direction)
return self.direction
def calculate_T(self,s,a): if a: return [(0.8, self.go(s, a)), (0.1, self.go(s, turn_right(a))), (0.1, self.go(s, turn_left(a)))] else: return [(0.0, s)]
def calculate_T(self, state, action):
if action:
return [(0.8, self.go(state, action)),
(0.1, self.go(state, turn_right(action))),
(0.1, self.go(state, turn_left(action)))]
else:
return [(0.0, state)]
def calculate_T(self, state, action, d_rand):
if action:
stoch = (1 - d_rand) / 2
return [(d_rand, self.go(state, action)),
(stoch, self.go(state, turn_right(action))),
(stoch, self.go(state, turn_left(action)))]
else:
return [(0.0, state)]
