本文整理汇总了Python中baselines.acktr.policies.GaussianMlpPolicy方法的典型用法代码示例。如果您正苦于以下问题：Python policies.GaussianMlpPolicy方法的具体用法？Python policies.GaussianMlpPolicy怎么用？Python policies.GaussianMlpPolicy使用的例子？那么恭喜您, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类baselines.acktr.policies的用法示例。
在下文中一共展示了policies.GaussianMlpPolicy方法的2个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: train
# 需要导入模块: from baselines.acktr import policies [as 别名]
# 或者: from baselines.acktr.policies import GaussianMlpPolicy [as 别名]
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
# 需要导入模块: from baselines.acktr import policies [as 别名]
# 或者: from baselines.acktr.policies import GaussianMlpPolicy [as 别名]
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()