def test_draw_hypothesis(self):
keepr = Keeper()
for i in range(1000):
keepr.update_reward_and_transition(self.s1, self.act_a, self.s2, 1.4)
hypothesis = Hypothesis.draw_hypothesis(self.model, keepr)
for next_state in self.model.get_next_states(self.s1):
self.assertGreater(hypothesis.get_transition(self.s1, self.act_a, next_state), 0)
places = 1
self.assertAlmostEqual(hypothesis.get_transition(self.s1, self.act_a, self.s2), 1, places)
self.assertAlmostEqual(hypothesis.get_reward(self.s1, self.act_a), 1.4, places)
def test_draw_hypothesis(self):
keepr = Keeper()
for i in range(1000):
keepr.update_reward_and_transition(self.s1, self.act_a, self.s2,
1.4)
hypothesis = Hypothesis.draw_hypothesis(self.model, keepr)
for next_state in self.model.get_next_states(self.s1):
self.assertGreater(
hypothesis.get_transition(self.s1, self.act_a, next_state), 0)
places = 1
self.assertAlmostEqual(
hypothesis.get_transition(self.s1, self.act_a, self.s2), 1, places)
self.assertAlmostEqual(hypothesis.get_reward(self.s1, self.act_a), 1.4,
places)
class RLAlgorithm(object):
def __init__(self):
self.keepr = Keeper()
self.model = Model()
# compute transition function P(s1, a, s2)
def get_transition(self, s1, a, s2):
return self.keepr.get_transition(s1, a, s2)
def get_reward(self, s1, a, s2):
return self.keepr.get_reward(s1, a, s2)
def get_transition_table(self, state, action):
return self.keepr.get_transition_table(state, action, self.model.get_next_states(state))
def get_reward_table(self, state, action):
return self.keepr.get_reward_table(state, state, action, self.model.get_next_states(state))
# update the transition model, keeping track of counts
def update_transition(self, s1, a, s2):
self.keepr.update_transition(s1, a, s2)
# keeping track of the reward model
def update_reward(self, s1, a, s2, r):
self.keepr.update_reward(s1, a, s2, r)
class RLAlgorithm(object):
def __init__(self):
self.keepr = Keeper()
self.model = Model()
# compute transition function P(s1, a, s2)
def get_transition(self, s1, a, s2):
return self.keepr.get_transition(s1, a, s2)
def get_reward(self, s1, a, s2):
return self.keepr.get_reward(s1, a, s2)
def get_transition_table(self, state, action):
return self.keepr.get_transition_table(
state, action, self.model.get_next_states(state))
def get_reward_table(self, state, action):
return self.keepr.get_reward_table(state, state, action,
self.model.get_next_states(state))
# update the transition model, keeping track of counts
def update_transition(self, s1, a, s2):
self.keepr.update_transition(s1, a, s2)
# keeping track of the reward model
def update_reward(self, s1, a, s2, r):
self.keepr.update_reward(s1, a, s2, r)
def __init__(self):
self.keepr = Keeper()
self.model = Model()
def __init__(self):
self.keepr = Keeper()
self.model = Model()