Missed TensorFlow Dev Summit? Check out the video playlist. Watch recordings

tf_agents.bandits.environments.non_stationary_stochastic_environment.EnvironmentDynamics

View source on GitHub

Abstract class to represent a non-stationary environment dynamics.

tf_agents.bandits.environments.non_stationary_stochastic_environment.EnvironmentDynamics(
    *args, **kwargs
)

This class is used with the NonStationaryStochasticEnvironment class below to obtain a non-stationary environment. To define a dynamics, derive from this class and define the abstract methods and properties below. To work correctly with graph and eager mode, Tensorflow variables must be defined in the constructor of this class. When used within a BanditTFEnvironment autodeps in reset and step functions will handle automatically the operation order.

Attributes:

  • action_spec: Specification of the actions.
  • batch_size: Returns the batch size used for observations and rewards.
  • name: Returns the name of this module as passed or determined in the ctor.

    NOTE: This is not the same as the self.name_scope.name which includes parent module names.

  • name_scope: Returns a tf.name_scope instance for this class.

  • observation_spec: Specification of the observations.

  • submodules: Sequence of all sub-modules.

    Submodules are modules which are properties of this module, or found as properties of modules which are properties of this module (and so on).

a = tf.Module()
b = tf.Module()
c = tf.Module()
a.b = b
b.c = c
assert list(a.submodules) == [b, c]
assert list(b.submodules) == [c]
assert list(c.submodules) == []
  • trainable_variables: Sequence of trainable variables owned by this module and its submodules.

  • variables: Sequence of variables owned by this module and its submodules.

Methods

observation

View source

observation(
    env_time
)

Returns an observation batch for the given time.

Args:

  • env_time: The scalar int64 tensor of the environment time step. This is incremented by the environment after the reward is computed.

Returns:

The observation batch with spec according to observation_spec.

reward

View source

reward(
    observation, env_time
)

Reward for the given observation and time step.

Args:

  • observation: A batch of observations with spec according to observation_spec.
  • env_time: The scalar int64 tensor of the environment time step. This is incremented by the environment after the reward is computed.

Returns:

A batch of rewards with spec shape [batch_size, num_actions] containing rewards for all arms.

with_name_scope

@classmethod
with_name_scope(
    cls, method
)

Decorator to automatically enter the module name scope.

class MyModule(tf.Module):
  @tf.Module.with_name_scope
  def __call__(self, x):
    if not hasattr(self, 'w'):
      self.w = tf.Variable(tf.random.normal([x.shape[1], 64]))
    return tf.matmul(x, self.w)

Using the above module would produce tf.Variables and tf.Tensors whose names included the module name:

mod = MyModule()
mod(tf.ones([8, 32]))
# ==> <tf.Tensor: ...>
mod.w
# ==> <tf.Variable ...'my_module/w:0'>

Args:

  • method: The method to wrap.

Returns:

The original method wrapped such that it enters the module's name scope.