def runRBFN(name,fromStruct):
'''
Takes the Brent trajectories as input, shuffles them, and then runs the RBFN regression algorithm
'''
rs = ReadSetupFile()
#state, command = getStateAndCommandData(BrentTrajectoriesFolder)
#stateAll, commandAll = dicToArray(state), dicToArray(command)
#print ("old:", stateAll[0])
stateAll, commandAll = stateAndCommandDataFromTrajs(loadStateCommandPairsByStartCoords(pathDataFolder + "TrajRepository/"))
#stateAll, commandAll = stateAndCommandDataFromTrajs(loadStateCommandPairsByStartCoords(BrentTrajectoriesFolder))
#print ("len:", len(commandAll[0]))
stateAll = np.vstack(np.array(stateAll))
commandAll = np.vstack(np.array(commandAll))
#print ("len global:", len(commandAll))
#print ("new:", commandAll[0])
#this works because both shuffles generate the same order, due to the seed
np.random.seed(0)
np.random.shuffle(stateAll)
np.random.seed(0)
np.random.shuffle(commandAll)
print("nombre d'echantillons: ", len(stateAll))
fa = rbfn(rs.numfeats,rs.inputDim,rs.outputDim)
fa.getTrainingData(stateAll, commandAll)
if fromStruct == True:
initFromExistingStruct(fa,rs.RBFNpath+name+".struct")
else:
initFromData(fa,rs.RBFNpath+name+".struct")
fa.train_reg_rbfn(rs.lamb)
fa.saveTheta(rs.RBFNpath + name+".theta")
def runRBFN(name, fromStruct):
"""
Takes the Brent trajectories as input, shuffles them, and then runs the RBFN regression algorithm
"""
rs = ReadSetupFile()
# state, command = getStateAndCommandData(BrentTrajectoriesFolder)
# stateAll, commandAll = dicToArray(state), dicToArray(command)
# print ("old:", stateAll[0])
stateAll, commandAll = stateAndCommandDataFromTrajs(
loadStateCommandPairsByStartCoords(pathDataFolder + "TrajRepository/")
)
# stateAll, commandAll = stateAndCommandDataFromTrajs(loadStateCommandPairsByStartCoords(BrentTrajectoriesFolder))
# print ("len:", len(commandAll[0]))
stateAll = np.vstack(np.array(stateAll))
commandAll = np.vstack(np.array(commandAll))
# print ("len global:", len(commandAll))
# print ("new:", commandAll[0])
# this works because both shuffles generate the same order, due to the seed
np.random.seed(0)
np.random.shuffle(stateAll)
np.random.seed(0)
np.random.shuffle(commandAll)
print("nombre d'echantillons: ", len(stateAll))
fa = rbfn(rs.numfeats, rs.inputDim, rs.outputDim)
fa.getTrainingData(stateAll, commandAll)
if fromStruct == True:
initFromExistingStruct(fa, rs.RBFNpath + name + ".struct")
else:
initFromData(fa, rs.RBFNpath + name + ".struct")
fa.train_reg_rbfn(rs.lamb)
fa.saveTheta(rs.RBFNpath + name + ".theta")
def initRBFNController(rs,filename):
'''
Initializes the controller allowing to compute the output from the input and the vector of parameters theta
Input: -rs: ReadSetup, class object
-fr, FileReading, class object
'''
#Initializes the function approximator with the number of feature used
fa = rbfn(rs.numfeats,rs.inputDim,rs.outputDim)
fa.loadFeatures(filename+".struct")
return fa
def initRBFNController(rs, filename):
'''
Initializes the controller allowing to compute the output from the input and the vector of parameters theta
Input: -rs: ReadSetup, class object
-fr, FileReading, class object
'''
#Initializes the function approximator with the number of feature used
fa = rbfn(rs.numfeats, rs.inputDim, rs.outputDim)
fa.loadFeatures(filename + ".struct")
return fa
def UnitTest():
fa = rbfn(3,2,3)
input, output = [], []
for i in range(10000):
x,y = rd.random(), rd.random()
input.append([x,y])
output.append([x*y, x-y, x+y])
fa.getTrainingData(np.vstack(np.array(input)), np.vstack(np.array(output)))
fa.saveFeatures("test.struct")
fa.setCentersAndWidths()
fa.train_rbfn()
fa.saveTheta("test.theta")
fa.loadTheta("test.theta")
for i in range(20):
x,y = 3*rd.random(), 3*rd.random()
approx = fa.computeOutput(np.array([x,y]))
print("in:", [x,y])
print(" out:", approx)
print(" real:", [x*y, x-y, x+y])
def UnitTest():
fa = rbfn(3, 2, 3)
input, output = [], []
for i in range(10000):
x, y = rd.random(), rd.random()
input.append([x, y])
output.append([x * y, x - y, x + y])
fa.getTrainingData(np.vstack(np.array(input)), np.vstack(np.array(output)))
fa.saveFeatures("test.struct")
fa.setCentersAndWidths()
fa.train_rbfn()
fa.saveTheta("test.theta")
fa.loadTheta("test.theta")
for i in range(20):
x, y = 3 * rd.random(), 3 * rd.random()
approx = fa.computeOutput(np.array([x, y]))
print("in:", [x, y])
print(" out:", approx)
print(" real:", [x * y, x - y, x + y])