tf_agents.bandits.environments.piecewise_stochastic_environment.PiecewiseStationaryDynamics

View source on GitHub

A piecewise stationary environment dynamics.

Inherits From: EnvironmentDynamics

This is a piecewise stationary environment which computes rewards as:

rewards(t) = observation(t) * observation_to_reward(i) + additive_reward(i)

where t is the environment time (env_time) and i is the index of each piece. The environment time is incremented after the reward is computed while the piece index is incremented at the end of the time interval. The parameters observation_to_reward(i), additive_reward(i), and the length of interval, are drawn from given distributions at the beginning of each temporal interval.

observation_distribution A distribution from tfp.distributions with shape [batch_size, observation_dim] Note that the values of batch_size and observation_dim are deduced from the distribution.
interval_distribution A scalar distribution from tfp.distributions. The value is casted to int64 to update the time range.
observation_to_reward_distribution A distribution from tfp.distributions with shape [observation_dim, num_actions]. The value observation_dim must match the second dimension of observation_distribution.
additive_reward_distribution A distribution from tfp.distributions with shape [num_actions]. This models the non-contextual behavior of the bandit.

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.

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
list(a.submodules) == [b, c]
True
list(b.submodules) == [c]
True
list(c.submodules) == []
True

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

compute_optimal_action

View source

compute_optimal_reward

View source

observation

View source

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 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

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], 3]))
    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([1, 2]))
<tf.Tensor: shape=(1, 3), dtype=float32, numpy=..., dtype=float32)>
mod.w
<tf.Variable 'my_module/Variable:0' shape=(2, 3) dtype=float32,
numpy=..., dtype=float32)>

Args
method The method to wrap.

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