def setup_algorithms(dist, training_data, n_x, n_a, n_y, delta):
start = time.time()
statistical_approximation = StatisticalApproximator(n_x, n_a, n_y, training_data, smoothing_mode='gaussian')
function_approximation = FunctionApproximation(n_x, n_a, n_y, training_data)
doctor_approximation = DoctorApproximator(n_x, n_a, n_y, training_data)
print("Initializing Constraint")
start = time.time()
constraintStatUpper = Constraint(training_data, n_a, n_y, approximator=statistical_approximation, delta=delta, bound='upper')
constraintFuncApprox = Constraint(training_data, n_a, n_y, approximator=function_approximation, delta=delta)
constraint_exact_func = TrueConstraint(dist, approximator=function_approximation, delta=delta)
print("Initializing the constraint took {:.3f} seconds".format(time.time() - start))
print("Initializing algorithms")
algorithms = [
#ConstrainedGreedy(n_x, n_a, n_y, training_data, constraintStatUpper, statistical_approximation,
# name='Constrained Greedy', label='CG'),
# ConstrainedGreedy(n_x, n_a, n_y, split_training_data, constraintStatLower, statistical_approximation,
# name='Constrained Greedy Lower', label='CG_L'),
ConstrainedGreedy(n_x, n_a, n_y, training_data, constraintFuncApprox, function_approximation,
name="Constrained Greedy FuncApprox", label="CG_F"),
#ConstrainedDynamicProgramming(n_x, n_a, n_y, training_data, constraintStatUpper,
# statistical_approximation),
ConstrainedDynamicProgramming(n_x, n_a, n_y, training_data, constraintFuncApprox,
function_approximation, name="Constrained Dynamic Programming FuncApprox", label="CDP_F"),
#NaiveGreedy(n_x, n_a, n_y, function_approximation, max_steps=n_a),
#NaiveGreedy(n_x, n_a, n_y, function_approximation, max_steps=n_a),
NaiveDynamicProgramming(n_x, n_a, n_y, training_data, constraintStatUpper, reward=-0.35),
Doctor(),
EmulatedDoctor(n_x, n_a, n_y, training_data, approximator=doctor_approximation)
]
return algorithms
def setup_algorithms(training_data, dist, delta):
start = time.time()
n_x = dist.n_x
n_a = dist.n_a
n_y = dist.n_y
statistical_approximation_prior = StatisticalApproximator(
n_x, n_a, n_y, training_data, smoothing_mode='gaussian')
constraint_upper = Constraint(training_data,
n_a,
n_y,
approximator=statistical_approximation_prior,
delta=delta,
bound='upper')
constraint_lower = Constraint(training_data,
n_a,
n_y,
approximator=statistical_approximation_prior,
delta=delta,
bound='lower')
constraint_exact = TrueConstraint(
dist, approximator=statistical_approximation_prior, delta=delta)
algorithms = [
#ConstrainedDynamicProgramming(n_x, n_a, n_y, training_data, constraint_upper, statistical_approximation_prior, name="Dynamic Programming Upper Bound", label="CDP_U"),
#ConstrainedDynamicProgramming(n_x, n_a, n_y, training_data, constraint_lower, statistical_approximation_prior, name="Dynamic Programming Lower bound", label="CDP_L"),
#ConstrainedDynamicProgramming(n_x, n_a, n_y, training_data, constraint_exact, statistical_approximation_prior, name="Dynamic Programming Exact Bound", label="CDP_E"),
ConstrainedGreedy(n_x,
n_a,
n_y,
training_data,
constraint_upper,
statistical_approximation_prior,
name="Greedy Upper Bound",
label="CG_U"),
ConstrainedGreedy(n_x,
n_a,
n_y,
training_data,
constraint_lower,
statistical_approximation_prior,
name="Greedy Lower Bound",
label="CG_L"),
ConstrainedGreedy(n_x,
n_a,
n_y,
training_data,
constraint_exact,
statistical_approximation_prior,
name="Greedy Exact Bound",
label="CG_E"),
]
print("Setting up algorithms took {:.3f} seconds".format(time.time() -
start))
return algorithms
def setup_algorithms(training_data, dist, delta, train=True):
start = time.time()
n_x = dist.n_x
n_a = dist.n_a
n_y = dist.n_y
statistical_approximation_prior = StatisticalApproximator(
n_x, n_a, n_y, training_data, smoothing_mode='gaussian')
constraint_prior = Constraint(training_data,
n_a,
n_y,
approximator=statistical_approximation_prior,
delta=delta)
constraint_prior = TrueConstraint(
dist, approximator=statistical_approximation_prior, delta=delta)
algorithms = [
ConstrainedDynamicProgramming(n_x,
n_a,
n_y,
training_data,
constraint_prior,
statistical_approximation_prior,
name="Constrained Dynamic Programming",
label="CDP"),
ConstrainedGreedy(n_x,
n_a,
n_y,
training_data,
constraint_prior,
statistical_approximation_prior,
name="Constrained Greedy",
label="CG"),
NaiveGreedy(n_x,
n_a,
n_y,
statistical_approximation_prior,
round(delta * (n_a - 1)) + 1,
name='Naive Greedy',
label='NG'),
NaiveDynamicProgramming(n_x,
n_a,
n_y,
training_data,
statistical_approximation_prior,
reward=-(delta + 0.0001),
name='Naive Dynamic Programming',
label='NDP'),
]
print("Setting up algorithms took {:.3f} seconds".format(time.time() -
start))
return algorithms
def setup_algorithms(training_data, dist, delta, train=True):
start = time.time()
n_x = dist.n_x
n_a = dist.n_a
n_y = dist.n_y
statistical_approximation_prior = StatisticalApproximator(
n_x, n_a, n_y, training_data, smoothing_mode='gaussian')
true_approximation = ExactApproximator(dist)
constraint_upper_stat = Constraint(
training_data,
n_a,
n_y,
approximator=statistical_approximation_prior,
delta=delta)
constraint_upper_true = Constraint(training_data,
n_a,
n_y,
approximator=true_approximation,
delta=delta)
constraint_exact_true = TrueConstraint(dist,
approximator=true_approximation,
delta=delta)
constraint_exat_stat = TrueConstraint(
dist, approximator=statistical_approximation_prior, delta=delta)
algorithms = [
ConstrainedDynamicProgramming(n_x,
n_a,
n_y,
training_data,
constraint_upper_stat,
statistical_approximation_prior,
name="Dynamic Programming Upper Stat",
label="CDP_US"),
ConstrainedDynamicProgramming(n_x,
n_a,
n_y,
training_data,
constraint_upper_true,
true_approximation,
name="Dynamic Programming Upper True",
label="CDP_UT"),
ConstrainedDynamicProgramming(n_x,
n_a,
n_y,
training_data,
constraint_exact_true,
true_approximation,
name="Dynamic Programming Exact True",
label="CDP_ET"),
ConstrainedDynamicProgramming(n_x,
n_a,
n_y,
training_data,
constraint_exat_stat,
statistical_approximation_prior,
name="Dynamic Programming Exact Stat",
label="CDP_ES"),
]
print("Setting up algorithms took {:.3f} seconds".format(time.time() -
start))
return algorithms
epsilon=epsilon)
constraintStatL = Constraint(split_training_data,
n_a,
n_y,
approximator=statistical_approximation,
delta=delta,
epsilon=epsilon,
bound='lower')
constraintTrue = Constraint(split_training_data,
n_a,
n_y,
approximator=true_approximation,
delta=delta,
epsilon=epsilon)
constraintCT = TrueConstraint(dist,
approximator=statistical_approximation,
delta=delta,
epsilon=epsilon)
constraintTT = TrueConstraint(dist,
approximator=true_approximation,
delta=delta,
epsilon=epsilon)
constraintFuncApprox = Constraint(split_training_data,
n_a,
n_y,
approximator=function_approximation,
delta=delta,
epsilon=epsilon)
print(
"Initializing the constraint took {:.3f} seconds".format(time.time() -
start))
print("Initializing statistical approximator")
start = time.time()
statistical_approximationPrior = StatisticalApproximator(n_x, n_a, n_y, split_training_data, smoothing_mode='gaussian')
statistical_approximationNone = StatisticalApproximator(n_x, n_a, n_y, split_training_data, smoothing_mode='none')
true_approximation = ExactApproximator(dist)
function_approximation = FunctionApproximation(n_x, n_a, n_y, split_training_data)
print("Initializing approximators took {:.3f} seconds".format(start - time.time()))
print("Initializing Constraint")
start = time.time()
constraintNone = Constraint(split_training_data, n_a, n_y, approximator=statistical_approximationNone, delta=delta, epsilon=epsilon)
constraintPrior = Constraint(split_training_data, n_a, n_y, approximator=statistical_approximationPrior, delta=delta, epsilon=epsilon)
constraintFunc = Constraint(split_training_data, n_a, n_y, approximator=function_approximation, delta=delta, epsilon=epsilon)
constraintATrue = Constraint(split_training_data, n_a, n_y, approximator=true_approximation, delta=delta, epsilon=epsilon)
constraintTrue = TrueConstraint(dist, approximator=true_approximation, delta=delta, epsilon=epsilon)
print("Initializing the constraint took {:.3f} seconds".format(time.time()-start))
print("Initializing algorithms")
algorithms = [
#ConstrainedDynamicProgramming(n_x, n_a, n_y, split_training_data, constraintNone, statistical_approximationNone, name="Dynamic Programming Uniform Prior", label="CDP_U"),
ConstrainedDynamicProgramming(n_x, n_a, n_y, split_training_data, constraintPrior, statistical_approximationPrior, name="Dynamic Programming Historical Prior", label="CDP_H"),
#ConstrainedDynamicProgramming(n_x, n_a, n_y, split_training_data, constraintFunc, function_approximation, name="Dynamic Programming Function Approximation", label="CDP_F"),
ConstrainedDynamicProgramming(n_x, n_a, n_y, split_training_data, constraintATrue, true_approximation, name="Dynamic Programming True", label="CDP_T"),
#ConstrainedGreedy(n_x, n_a, n_y, split_training_data, constraintNone, statistical_approximationNone, name="Greedy Uniform Prior", label="CG_U"),
ConstrainedGreedy(n_x, n_a, n_y, split_training_data, constraintPrior, statistical_approximationPrior, name="Greedy Historical Prior", label="CG_H"),
#ConstrainedGreedy(n_x, n_a, n_y, split_training_data, constraintFunc, function_approximation, name="Greedy Function Approximation", label="CG_F"),
]
assert len(algorithms) == n_algorithms