本文整理匯總了Python中baselines.acktr.value_functions.NeuralNetValueFunction方法的典型用法代碼示例。如果您正苦於以下問題：Python value_functions.NeuralNetValueFunction方法的具體用法？Python value_functions.NeuralNetValueFunction怎麽用？Python value_functions.NeuralNetValueFunction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baselines.acktr.value_functions的用法示例。
在下文中一共展示了value_functions.NeuralNetValueFunction方法的2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: train
# 需要導入模塊: from baselines.acktr import value_functions [as 別名]
# 或者: from baselines.acktr.value_functions import NeuralNetValueFunction [as 別名]
def train(env_id, num_timesteps, seed):
env = make_mujoco_env(env_id, seed)
with tf.Session(config=tf.ConfigProto()):
ob_dim = env.observation_space.shape[0]
ac_dim = env.action_space.shape[0]
with tf.variable_scope("vf"):
vf = NeuralNetValueFunction(ob_dim, ac_dim)
with tf.variable_scope("pi"):
policy = GaussianMlpPolicy(ob_dim, ac_dim)
learn(env, policy=policy, vf=vf,
gamma=0.99, lam=0.97, timesteps_per_batch=2500,
desired_kl=0.002,
num_timesteps=num_timesteps, animate=False)
env.close() 示例2: train
# 需要導入模塊: from baselines.acktr import value_functions [as 別名]
# 或者: from baselines.acktr.value_functions import NeuralNetValueFunction [as 別名]
def train(env_id, num_timesteps, seed):
env=gym.make(env_id)
env = bench.Monitor(env, logger.get_dir() and os.path.join(logger.get_dir(), str(rank)))
set_global_seeds(seed)
env.seed(seed)
gym.logger.setLevel(logging.WARN)
with tf.Session(config=tf.ConfigProto()):
ob_dim = env.observation_space.shape[0]
ac_dim = env.action_space.shape[0]
with tf.variable_scope("vf"):
vf = NeuralNetValueFunction(ob_dim, ac_dim)
with tf.variable_scope("pi"):
policy = GaussianMlpPolicy(ob_dim, ac_dim)
learn(env, policy=policy, vf=vf,
gamma=0.99, lam=0.97, timesteps_per_batch=2500,
desired_kl=0.002,
num_timesteps=num_timesteps, animate=False)
env.close()