tf_agents.bandits.environments.piecewise_stochastic_environment.PiecewiseStationaryDynamics

A piecewise stationary environment dynamics.

Inherits From: EnvironmentDynamics

tf_agents.bandits.environments.piecewise_stochastic_environment.PiecewiseStationaryDynamics(
    observation_distribution: types.Distribution,
    interval_distribution: types.Distribution,
    observation_to_reward_distribution: types.Distribution,
    additive_reward_distribution: types.Distribution
)

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.
observation_spec Specification of the observations.

Methods

compute_optimal_action

View source

compute_optimal_action(
    observation: tf_agents.typing.types.NestedTensor
) -> tf_agents.typing.types.NestedTensor

compute_optimal_reward

View source

compute_optimal_reward(
    observation: tf_agents.typing.types.NestedTensor
) -> tf_agents.typing.types.NestedTensor

observation

View source

observation(
    unused_t
) -> tf_agents.typing.types.NestedTensor

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: tf_agents.typing.types.NestedTensor,
    t: tf_agents.typing.types.Int
) -> tf_agents.typing.types.NestedTensor

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.