Python tf_util.ensure_tf_input方法代码示例

# 需要导入模块: from baselines.common import tf_util [as 别名]
# 或者: from baselines.common.tf_util import ensure_tf_input [as 别名]
def build_act(make_obs_ph, q_func, num_actions, scope="deepq", reuse=None):
    """Creates the act function:

    Parameters
    ----------
    make_obs_ph: str -> tf.placeholder or TfInput
        a function that take a name and creates a placeholder of input with that name
    q_func: (tf.Variable, int, str, bool) -> tf.Variable
        the model that takes the following inputs:
            observation_in: object
                the output of observation placeholder
            num_actions: int
                number of actions
            scope: str
            reuse: bool
                should be passed to outer variable scope
        and returns a tensor of shape (batch_size, num_actions) with values of every action.
    num_actions: int
        number of actions.
    scope: str or VariableScope
        optional scope for variable_scope.
    reuse: bool or None
        whether or not the variables should be reused. To be able to reuse the scope must be given.

    Returns
    -------
    act: (tf.Variable, bool, float) -> tf.Variable
        function to select and action given observation.
`       See the top of the file for details.
    """
    with tf.variable_scope(scope, reuse=reuse):
        observations_ph = U.ensure_tf_input(make_obs_ph("observation"))
        stochastic_ph = tf.placeholder(tf.bool, (), name="stochastic")
        update_eps_ph = tf.placeholder(tf.float32, (), name="update_eps")

        eps = tf.get_variable("eps", (), initializer=tf.constant_initializer(0))

        q_values = q_func(observations_ph.get(), num_actions, scope="q_func")
        deterministic_actions = tf.argmax(q_values, axis=1)

        batch_size = tf.shape(observations_ph.get())[0]
        random_actions = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=num_actions, dtype=tf.int64)
        chose_random = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=1, dtype=tf.float32) < eps
        stochastic_actions = tf.where(chose_random, random_actions, deterministic_actions)

        output_actions = tf.cond(stochastic_ph, lambda: stochastic_actions, lambda: deterministic_actions)
        update_eps_expr = eps.assign(tf.cond(update_eps_ph >= 0, lambda: update_eps_ph, lambda: eps))
        act = U.function(inputs=[observations_ph, stochastic_ph, update_eps_ph],
                         outputs=output_actions,
                         givens={update_eps_ph: -1.0, stochastic_ph: True},
                         updates=[update_eps_expr])
        return act 

# 需要导入模块: from baselines.common import tf_util [as 别名]
# 或者: from baselines.common.tf_util import ensure_tf_input [as 别名]
def build_act(make_obs_ph, q_func, num_actions, noisy=False, scope="deepq", reuse=None):
    """Creates the act function:

    Parameters
    ----------
    make_obs_ph: str -> tf.placeholder or TfInput
        a function that take a name and creates a placeholder of input with that name
    q_func: (tf.Variable, int, str, bool) -> tf.Variable
        the model that takes the following inputs:
            observation_in: object
                the output of observation placeholder
            num_actions: int
                number of actions
            scope: str
            reuse: bool
                should be passed to outer variable scope
        and returns a tensor of shape (batch_size, num_actions) with values of every action.
    num_actions: int
        number of actions.
    scope: str or VariableScope
        optional scope for variable_scope.
    reuse: bool or None
        whether or not the variables should be reused. To be able to reuse the scope must be given.

    Returns
    -------
    act: (tf.Variable, bool, float) -> tf.Variable
        function to select and action given observation.
`       See the top of the file for details.
    """
    with tf.variable_scope(scope, reuse=reuse):
        observations_ph = U.ensure_tf_input(make_obs_ph("observation"))
        stochastic_ph = tf.placeholder(tf.bool, (), name="stochastic")
        update_eps_ph = tf.placeholder(tf.float32, (), name="update_eps")

        eps = tf.get_variable("eps", (), initializer=tf.constant_initializer(0))

        q_values = q_func(observations_ph.get(), num_actions, scope="q_func", noisy=noisy)
        deterministic_actions = tf.argmax(q_values, axis=1)

        batch_size = tf.shape(observations_ph.get())[0]
        random_actions = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=num_actions, dtype=tf.int64)
        chose_random = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=1, dtype=tf.float32) < eps
        stochastic_actions = tf.where(chose_random, random_actions, deterministic_actions)

        output_actions = tf.cond(stochastic_ph, lambda: stochastic_actions, lambda: deterministic_actions)
        update_eps_expr = eps.assign(tf.cond(update_eps_ph >= 0, lambda: update_eps_ph, lambda: eps))

        act = U.function(inputs=[observations_ph, stochastic_ph, update_eps_ph],
                         outputs=output_actions,
                         givens={update_eps_ph: -1.0, stochastic_ph: True},
                         updates=[update_eps_expr])
                         
        return act 

# 需要导入模块: from baselines.common import tf_util [as 别名]
# 或者: from baselines.common.tf_util import ensure_tf_input [as 别名]
def build_act(make_obs_ph, q_func, num_actions, scope="deepq", reuse=None):
  """Creates the act function:

  Parameters
  ----------
  make_obs_ph: str -> tf.placeholder or TfInput
      a function that take a name and creates a placeholder of input with that name
  q_func: (tf.Variable, int, str, bool) -> tf.Variable
      the model that takes the following inputs:
          observation_in: object
              the output of observation placeholder
          num_actions: int
              number of actions
          scope: str
          reuse: bool
              should be passed to outer variable scope
      and returns a tensor of shape (batch_size, num_actions) with values of every action.
  num_actions: int
      number of actions.
  scope: str or VariableScope
      optional scope for variable_scope.
  reuse: bool or None
      whether or not the variables should be reused. To be able to reuse the scope must be given.

  Returns
  -------
  act: (tf.Variable, bool, float) -> tf.Variable
      function to select and action given observation.
`       See the top of the file for details.
  """
  with tf.variable_scope(scope, reuse=reuse):
    observations_ph = U.ensure_tf_input(make_obs_ph("observation"))
    stochastic_ph = tf.placeholder(tf.bool, (), name="stochastic")
    update_eps_ph = tf.placeholder(tf.float32, (), name="update_eps")

    eps = tf.get_variable("eps", (), initializer=tf.constant_initializer(0))

    q_values = q_func(observations_ph.get(), num_actions, scope="q_func")
    deterministic_actions = tf.argmax(q_values, axis=1)

    batch_size = tf.shape(observations_ph.get())[0]
    random_actions = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=num_actions, dtype=tf.int64)
    chose_random = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=1, dtype=tf.float32) < eps
    stochastic_actions = tf.where(chose_random, random_actions, deterministic_actions)

    output_actions = tf.cond(stochastic_ph, lambda: stochastic_actions, lambda: deterministic_actions)
    update_eps_expr = eps.assign(tf.cond(update_eps_ph >= 0, lambda: update_eps_ph, lambda: eps))
    act = U.function(inputs=[observations_ph, stochastic_ph, update_eps_ph],
                     outputs=output_actions,
                     givens={update_eps_ph: -1.0, stochastic_ph: True},
                     updates=[update_eps_expr])
    return act 

# 需要导入模块: from baselines.common import tf_util [as 别名]
# 或者: from baselines.common.tf_util import ensure_tf_input [as 别名]
def build_act(make_obs_ph, p_dist_func, num_actions, dist_params, scope="distdeepq", reuse=None):
    """Creates the act function:

    Parameters
    ----------
    make_obs_ph: str -> tf.placeholder or TfInput
        a function that take a name and creates a placeholder of input with that name
    p_dist_func: (tf.Variable, int, str, bool) -> tf.Variable
        the model that takes the following inputs:
            observation_in: object
                the output of observation placeholder
            num_actions: int
                number of actions
            scope: str
            reuse: bool
                should be passed to outer variable scope
        and returns a tensor of shape (batch_size, num_actions) with values of every action.
    num_actions: int
        number of actions.
    scope: str or VariableScope
        optional scope for variable_scope.
    reuse: bool or None
        whether or not the variables should be reused. To be able to reuse the scope must be given.

    Returns
    -------
    act: (tf.Variable, bool, float) -> tf.Variable
        function to select and action given observation.
`       See the top of the file for details.
    """
    with tf.variable_scope(scope, reuse=reuse):
        observations_ph = U.ensure_tf_input(make_obs_ph("observation"))
        stochastic_ph = tf.placeholder(tf.bool, (), name="stochastic")
        update_eps_ph = tf.placeholder(tf.float32, (), name="update_eps")

        eps = tf.get_variable("eps", (), initializer=tf.constant_initializer(0))

        p_values = p_dist_func(observations_ph.get(), num_actions, dist_params['nb_atoms'], scope="q_func")
        deterministic_actions = pick_action(p_values, dist_params)

        batch_size = tf.shape(observations_ph.get())[0]
        random_actions = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=num_actions, dtype=tf.int64)
        chose_random = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=1, dtype=tf.float32) < eps
        stochastic_actions = tf.where(chose_random, random_actions, deterministic_actions)

        output_actions = tf.cond(stochastic_ph, lambda: stochastic_actions, lambda: deterministic_actions)
        update_eps_expr = eps.assign(tf.cond(update_eps_ph >= 0, lambda: update_eps_ph, lambda: eps))
        act = U.function(inputs=[observations_ph, stochastic_ph, update_eps_ph],
                         outputs=output_actions,
                         givens={update_eps_ph: -1.0, stochastic_ph: True},
                         updates=[update_eps_expr])
        return act 

# 需要导入模块: from baselines.common import tf_util [as 别名]
# 或者: from baselines.common.tf_util import ensure_tf_input [as 别名]
def build_act(make_obs_ph, q_func, num_actions, scope="deepq", reuse=None):
    """Creates the act function:

    Parameters
    ----------
    make_obs_ph: str -> tf.placeholder or TfInput
        a function that take a name and creates a placeholder of input with that name
    q_func: (tf.Variable, int, str, bool) -> tf.Variable
        the model that takes the following inputs:
            observation_in: object
                the output of observation placeholder
            num_actions: int
                number of actions
            scope: str
            reuse: bool
                should be passed to outer variable scope
        and returns a tensor of shape (batch_size, num_actions) with values of every action.
    num_actions: int
        number of actions.
    scope: str or VariableScope
        optional scope for variable_scope.
    reuse: bool or None
        whether or not the variables should be reused. To be able to reuse the scope must be given.

    Returns
    -------
    act: (tf.Variable, bool, float) -> tf.Variable
        function to select and action given observation.
`       See the top of the file for details.
    """
    with tf.variable_scope(scope, reuse=reuse):
        observations_ph = U.ensure_tf_input(make_obs_ph("observation"))
        stochastic_ph = tf.placeholder(tf.bool, (), name="stochastic")
        update_eps_ph = tf.placeholder(tf.float32, (), name="update_eps")

        eps = tf.get_variable("eps", (), initializer=tf.constant_initializer(0))

        q_values = q_func(observations_ph.get(), num_actions, scope="q_func")
        deterministic_actions = tf.argmax(q_values, axis=1)

        batch_size = tf.shape(observations_ph.get())[0]
        random_actions = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=num_actions, dtype=tf.int64)
        chose_random = tf.random_uniform(tf.stack([batch_size]), minval=0, maxval=1, dtype=tf.float32) < eps
        stochastic_actions = tf.where(chose_random, random_actions, deterministic_actions)

        output_actions = tf.cond(stochastic_ph, lambda: stochastic_actions, lambda: deterministic_actions)
        update_eps_expr = eps.assign(tf.cond(update_eps_ph >= 0, lambda: update_eps_ph, lambda: eps))

        act = U.function(inputs=[observations_ph, stochastic_ph, update_eps_ph],
                         outputs=output_actions,
                         givens={update_eps_ph: -1.0, stochastic_ph: True},
                         updates=[update_eps_expr])
        return act