spinup/algos/tf1/trpo/core.py [19:49]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def placeholder(dim=None):
    return tf.placeholder(dtype=tf.float32, shape=combined_shape(None,dim))

def placeholders(*args):
    return [placeholder(dim) for dim in args]

def placeholder_from_space(space):
    if isinstance(space, Box):
        return placeholder(space.shape)
    elif isinstance(space, Discrete):
        return tf.placeholder(dtype=tf.int32, shape=(None,))
    raise NotImplementedError

def placeholders_from_spaces(*args):
    return [placeholder_from_space(space) for space in args]

def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
    for h in hidden_sizes[:-1]:
        x = tf.layers.dense(x, units=h, activation=activation)
    return tf.layers.dense(x, units=hidden_sizes[-1], activation=output_activation)

def get_vars(scope=''):
    return [x for x in tf.trainable_variables() if scope in x.name]

def count_vars(scope=''):
    v = get_vars(scope)
    return sum([np.prod(var.shape.as_list()) for var in v])

def gaussian_likelihood(x, mu, log_std):
    pre_sum = -0.5 * (((x-mu)/(tf.exp(log_std)+EPS))**2 + 2*log_std + np.log(2*np.pi))
    return tf.reduce_sum(pre_sum, axis=1)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



spinup/algos/tf1/vpg/core.py [13:43]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
def placeholder(dim=None):
    return tf.placeholder(dtype=tf.float32, shape=combined_shape(None,dim))

def placeholders(*args):
    return [placeholder(dim) for dim in args]

def placeholder_from_space(space):
    if isinstance(space, Box):
        return placeholder(space.shape)
    elif isinstance(space, Discrete):
        return tf.placeholder(dtype=tf.int32, shape=(None,))
    raise NotImplementedError

def placeholders_from_spaces(*args):
    return [placeholder_from_space(space) for space in args]

def mlp(x, hidden_sizes=(32,), activation=tf.tanh, output_activation=None):
    for h in hidden_sizes[:-1]:
        x = tf.layers.dense(x, units=h, activation=activation)
    return tf.layers.dense(x, units=hidden_sizes[-1], activation=output_activation)

def get_vars(scope=''):
    return [x for x in tf.trainable_variables() if scope in x.name]

def count_vars(scope=''):
    v = get_vars(scope)
    return sum([np.prod(var.shape.as_list()) for var in v])

def gaussian_likelihood(x, mu, log_std):
    pre_sum = -0.5 * (((x-mu)/(tf.exp(log_std)+EPS))**2 + 2*log_std + np.log(2*np.pi))
    return tf.reduce_sum(pre_sum, axis=1)
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -