__author__ = 'Tom Schaul, [email protected]' from pybrain.rl.tasks.capturegame import CaptureGameTask from pybrain.structure.evolvables.cheaplycopiable import CheaplyCopiable from pybrain.rl.learners import ES from pybrain.utilities import storeCallResults from pybrain.rl.agents.capturegameplayers.killing import KillingPlayer # task settings: opponent, averaging to reduce noise, board size, etc. size = 5 simplenet = False task = CaptureGameTask(size, averageOverGames=40, opponent=KillingPlayer) # keep track of evaluations for plotting res = storeCallResults(task) if simplenet: # simple network from pybrain.tools.shortcuts import buildNetwork from pybrain import SigmoidLayer net = buildNetwork(task.outdim, task.indim, outclass=SigmoidLayer) else: # specialized mdrnn variation from pybrain.structure.networks.custom.capturegame import CaptureGameNetwork net = CaptureGameNetwork(size=size, hsize=2, simpleborders=True) net = CheaplyCopiable(net) print net.name, 'has', net.paramdim, 'trainable parameters.' learner = ES(task, net, mu=5, lambada=5, verbose=True, noisy=True)
""" An illustration of using the NSGA-II multi-objective optimization algorithm on a simple standard benchmark function. """ __author__ = 'Tom Schaul, [email protected]' from pybrain.rl.learners.blackboxoptimizers.evolution.nsga2 import MultiObjectiveGA from pybrain.rl.environments.functions.multiobjective import KurBenchmark from pybrain.utilities import storeCallResults import pylab from scipy import zeros # The benchmark function f = KurBenchmark() # keep track of all evaluations res = storeCallResults(f) # start at the origin x0 = zeros(f.indim) # the optimization for a maximum of 2500 function evaluations n = MultiObjectiveGA(f, x0) n.learn(2500) # plotting the results (blue = all evaluated points, red = resulting pareto front) for x in res: pylab.plot([x[1]], [x[0]], 'b+') for x in n.bestEvaluation: pylab.plot([x[1]], [x[0]], 'ro') pylab.show()
__author__ = 'Tom Schaul, [email protected]' from pybrain.rl.environments.twoplayergames import CaptureGameTask from pybrain.structure.evolvables.cheaplycopiable import CheaplyCopiable from pybrain.optimization import ES from pybrain.utilities import storeCallResults from pybrain.rl.environments.twoplayergames.capturegameplayers.killing import KillingPlayer # task settings: opponent, averaging to reduce noise, board size, etc. size = 5 simplenet = False task = CaptureGameTask(size, averageOverGames = 40, opponent = KillingPlayer) # keep track of evaluations for plotting res = storeCallResults(task) if simplenet: # simple network from pybrain.tools.shortcuts import buildNetwork from pybrain import SigmoidLayer net = buildNetwork(task.outdim, task.indim, outclass = SigmoidLayer) else: # specialized mdrnn variation from pybrain.structure.networks.custom.capturegame import CaptureGameNetwork net = CaptureGameNetwork(size = size, hsize = 2, simpleborders = True) net = CheaplyCopiable(net) print net.name, 'has', net.paramdim, 'trainable parameters.' learner = ES(task, net, mu = 5, lambada = 5,
""" An illustration of using the NSGA-II multi-objective optimization algorithm on a simple standard benchmark function. """ __author__ = 'Tom Schaul, [email protected]' from pybrain.rl.learners.blackboxoptimizers.evolution.nsga2 import MultiObjectiveGA from pybrain.rl.environments.functions.multiobjective import KurBenchmark from pybrain.utilities import storeCallResults import pylab from scipy import zeros # The benchmark function f = KurBenchmark() # keep track of all evaluations res = storeCallResults(f) # start at the origin x0 = zeros(f.indim) # the optimization for a maximum of 2500 function evaluations n = MultiObjectiveGA(f, x0) n.learn(2500) # plotting the results (blue = all evaluated points, red = resulting pareto front) for x in res: pylab.plot([x[1]], [x[0]], 'b+') for x in n.bestEvaluation: pylab.plot([x[1]], [x[0]], 'ro') pylab.show()