tf_agents.metrics.batched_py_metric.BatchedPyMetric

Wrapper for batching metrics.

Inherits From: PyStepMetric

This can be used to wrap any python metric that takes a single trajectory to produce a batched version of the metric that takes a batch of trajectories.

prefix Prefix for the metric.
summary_op TF summary op for this metric.
summary_placeholder TF placeholder to be used for the result of this metric.

Methods

aggregate

View source

Aggregates a list of metrics.

The default behaviour is to return the average of the metrics.

Args
metrics a list of metrics, of the same class.

Returns
The result of aggregating this metric.

build

View source

call

View source

Processes the batched_trajectory to update the metric.

Args
batched_trajectory A Trajectory containing batches of experience.

Raises
ValueError If the batch size is an unexpected value.

log

View source

reset

View source

Resets internal stat gathering variables used to compute the metric.

result

View source

Evaluates the current value of the metric.

tf_summaries

View source

Build TF summary op and placeholder for this metric.

To execute the op, call py_metric.run_summaries.

Args
train_step Step counter for training iterations. If None, no metric is generated against the global step.
step_metrics Step values to plot as X axis in addition to global_step.

Returns
The summary op.

Raises
RuntimeError If this method has already been called (it can only be called once).
ValueError If any item in step_metrics is not of type PyMetric or tf_metric.TFStepMetric.

__call__

View source

Method to update the metric contents.

To change the behavior of this function, override the call method.

Different subclasses might use this differently. For instance, the PyStepMetric takes in a trajectory, while the CounterMetric takes no parameters.

Args
*args See call method of subclass for specific arguments.