# Module: tf_agents.metrics.py_metrics

<br />

|---|
| [![](https://www.tensorflow.org/images/GitHub-Mark-32px.png) View source on GitHub](https://github.com/tensorflow/agents/blob/v0.19.0/tf_agents/metrics/py_metrics.py) |

Implementation of various python metrics.

## Classes

[`class AverageEpisodeLengthMetric`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/metrics/py_metrics/AverageEpisodeLengthMetric): Computes the average episode length.

[`class AverageReturnMetric`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/metrics/py_metrics/AverageReturnMetric): Computes the average undiscounted reward.

[`class CounterMetric`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/metrics/py_metrics/CounterMetric): Metric to track an arbitrary counter.

[`class EnvironmentSteps`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/metrics/py_metrics/EnvironmentSteps): Counts the number of steps taken in the environment.

[`class NumberOfEpisodes`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/metrics/py_metrics/NumberOfEpisodes): Counts the number of episodes in the environment.

[`class NumpyDeque`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/metrics/py_metrics/NumpyDeque): Deque implementation using a numpy array as a circular buffer.

[`class StreamingMetric`](https://www.tensorflow.org/agents/api_docs/python/tf_agents/metrics/py_metrics/StreamingMetric): Abstract base class for streaming metrics.

<br />

<br />

<br />

| ## Other Members ||
|---|---|
| absolute_import | Instance of `__future__._Feature` |
| division | Instance of `__future__._Feature` |
| print_function | Instance of `__future__._Feature` |

<br />