class QModel(object):
def __init__(self, config):
self.features = FeatureFunctionVector(config["features"])
self.initialize_weights(config["initial_weights"])
def initialize_weights(self, config):
n = self.features.length()
if config["type"] == "uniform_random":
self.weights = (np.random.random((n,)) * 2.0) - 1.0
elif config["type"] == "zero":
self.weights = np.zeros((n,))
elif config["type"] == "explicit":
name_to_weights = config["values"]
names_and_lengths = self.features.names_and_lengths()
assert set(name_to_weights.keys()) == set(list(n for n, l in names_and_lengths))
weights_list = []
for name, length in names_and_lengths:
ws = name_to_weights[name]
assert length == len(
ws
), "Length {} does not equal number of weights specified {} for weight named {}".format(
length, len(ws), name
)
weights_list.extend(ws)
self.weights = np.array(weights_list, dtype=np.float_)
else:
raise Exception(
"Unexpected type: {}. Possibilities are: {}".format(
config["type"], ["uniform_random", "zero", "explicit"]
)
)
def q(self, s, a):
return self.weights.dot(self.features.f(s, a))
def beta(self, s, a):
return self.features.f(s, a)
def update_weights(self, delta):
self.weights += delta
def save_model(self, fn):
np.savetxt(fn, self.weights)
class QModel(object):
def __init__(self, config):
self.features = FeatureFunctionVector(config["features"])
self.initialize_weights(config["initial_weights"])
def initialize_weights(self, config):
n = self.features.length()
if config["type"] == "uniform_random":
self.weights = (np.random.random((n, )) * 2.0) - 1.0
elif config["type"] == "zero":
self.weights = np.zeros((n, ))
elif config["type"] == "explicit":
name_to_weights = config["values"]
names_and_lengths = self.features.names_and_lengths()
assert set(name_to_weights.keys()) == set(
list(n for n, l in names_and_lengths))
weights_list = []
for name, length in names_and_lengths:
ws = name_to_weights[name]
assert length == len(
ws
), "Length {} does not equal number of weights specified {} for weight named {}".format(
length, len(ws), name)
weights_list.extend(ws)
self.weights = np.array(weights_list, dtype=np.float_)
else:
raise Exception(
"Unexpected type: {}. Possibilities are: {}".format(
config["type"], ["uniform_random", "zero", "explicit"]))
def q(self, s, a):
return self.weights.dot(self.features.f(s, a))
def beta(self, s, a):
return self.features.f(s, a)
def update_weights(self, delta):
self.weights += delta
def save_model(self, fn):
np.savetxt(fn, self.weights)
def __init__(self, config):
self.features = FeatureFunctionVector(config["features"])
self.initialize_weights(config["initial_weights"])
def __init__(self, config):
self.features = FeatureFunctionVector(config["features"])
self.initialize_weights(config["initial_weights"])
