# {py:mod}`evorl.algorithms.contrib.pop_ppo`

```{py:module} evorl.algorithms.contrib.pop_ppo
```

```{autodoc2-docstring} evorl.algorithms.contrib.pop_ppo
:parser: autodoc2_docstrings_parser
:allowtitles:
```

## Module Contents

### Classes

````{list-table}
:class: autosummary longtable
:align: left

* - {py:obj}`PopPPOWorkflow <evorl.algorithms.contrib.pop_ppo.PopPPOWorkflow>`
  -
````

### API

`````{py:class} PopPPOWorkflow(env: evorl.envs.Env, agent: evorl.agent.Agent, optimizer: optax.GradientTransformation, evaluator: evorl.evaluators.Evaluator, config: omegaconf.DictConfig)
:canonical: evorl.algorithms.contrib.pop_ppo.PopPPOWorkflow

Bases: {py:obj}`evorl.algorithms.ppo.PPOWorkflow`

````{py:method} build_from_config(config: omegaconf.DictConfig, enable_multi_devices: bool = False, enable_jit: bool = True) -> typing_extensions.Self
:canonical: evorl.algorithms.contrib.pop_ppo.PopPPOWorkflow.build_from_config
:classmethod:

````

````{py:method} evaluate(state)
:canonical: evorl.algorithms.contrib.pop_ppo.PopPPOWorkflow.evaluate

````

````{py:method} learn(state: evorl.types.State) -> evorl.types.State
:canonical: evorl.algorithms.contrib.pop_ppo.PopPPOWorkflow.learn

````

````{py:method} name()
:canonical: evorl.algorithms.contrib.pop_ppo.PopPPOWorkflow.name
:classmethod:

````

````{py:method} setup(key: chex.PRNGKey) -> evorl.types.State
:canonical: evorl.algorithms.contrib.pop_ppo.PopPPOWorkflow.setup

```{autodoc2-docstring} evorl.algorithms.contrib.pop_ppo.PopPPOWorkflow.setup
:parser: autodoc2_docstrings_parser
```

````

````{py:method} step(state: evorl.types.State) -> tuple[evorl.metrics.MetricBase, evorl.types.State]
:canonical: evorl.algorithms.contrib.pop_ppo.PopPPOWorkflow.step

````

`````