tf_agents.bandits.agents.linear_bandit_agent.update_a_and_b_with_forgetting

Stay organized with collections Save and categorize content based on your preferences.

View source on GitHub

Update the covariance matrix a and the weighted sum of rewards b.

tf_agents.bandits.agents.linear_bandit_agent.update_a_and_b_with_forgetting(
    a_prev: tf_agents.typing.types.Tensor,
    b_prev: tf_agents.typing.types.Tensor,
    r: tf_agents.typing.types.Tensor,
    x: tf_agents.typing.types.Tensor,
    gamma: float
) -> Tuple[tf_agents.typing.types.Tensor, tf_agents.typing.types.Tensor]

This function updates the covariance matrix a and the sum of weighted rewards b using a forgetting factor gamma.

Args
a_prev	previous estimate of a.
b_prev	previous estimate of b.
r	a Tensor of shape [batch_size]. This is the rewards of the batched observations.
x	a Tensor of shape [batch_size, context_dim]. This is the matrix with the (batched) observations.
gamma	a float forgetting factor in [0.0, 1.0].

Returns
The updated estimates of a and b.