本文整理匯總了Python中pybrain.rl.experiments.Experiment.allRewards方法的典型用法代碼示例。如果您正苦於以下問題：Python Experiment.allRewards方法的具體用法？Python Experiment.allRewards怎麽用？Python Experiment.allRewards使用的例子？那麽, 這裏精選的方法代碼示例或許可以為您提供幫助。您也可以進一步了解該方法所在類pybrain.rl.experiments.Experiment的用法示例。
在下文中一共展示了Experiment.allRewards方法的1個代碼示例，這些例子默認根據受歡迎程度排序。您可以為喜歡或者感覺有用的代碼點讚，您的評價將有助於係統推薦出更棒的Python代碼示例。
示例1: initExperiment
# 需要導入模塊: from pybrain.rl.experiments import Experiment [as 別名]
# 或者: from pybrain.rl.experiments.Experiment import allRewards [as 別名]
def initExperiment(alg, optimistic=True):
env = Maze(envmatrix, (7, 7))
# create task
task = MDPMazeTask(env)
# create value table and initialize with ones
table = ActionValueTable(81, 4)
if optimistic:
table.initialize(1.)
else:
table.initialize(0.)
# create agent with controller and learner - use SARSA(), Q() or QLambda() here
learner = alg()
# standard exploration is e-greedy, but a different type can be chosen as well
# learner.explorer = BoltzmannExplorer()
agent = LearningAgent(table, learner)
agent.batchMode = False
experiment = Experiment(task, agent)
experiment.allRewards = []
return experiment