evorl.workflows.workflow

Module Contents

Classes

AbstractWorkflow	A Workflow Interface for EvoRL training pipelines.
Workflow	The base class for all Workflows.

API

class evorl.workflows.workflow.AbstractWorkflow

Bases: abc.ABC

A Workflow Interface for EvoRL training pipelines.

abstract init(key: chex.PRNGKey) → evorl.types.State

Initialize the workflow’s state.

Parameters:

key – JAX PRNGKey

Returns:

the state of the workflow

Return type:

state

classmethod name() → str

Define the name of the workflow (eg. PPO, PSO, etc.).

Default workflow name is its class name.

abstract step(state: evorl.types.State) → tuple[Any, evorl.types.State]

Define the logic of one training iteration.

class evorl.workflows.workflow.Workflow(config: omegaconf.DictConfig)

Bases: evorl.workflows.workflow.AbstractWorkflow

The base class for all Workflows.

All workflow classes are inherit from this class, and customize by implementing

add_recorders(recorders: evorl.recorders.Recorder) → None

abstract classmethod build_from_config(config: omegaconf.DictConfig, *args, **kwargs) → typing_extensions.Self

Build the workflow instance from the config.

This is the public API to call for instantiating a new workflow object from config. Normally, it will call init() and do some pre- and post-processing.

Parameters:

config – config object

Returns:

A workflow instance

close() → None

Close the workflow’s components.

init(key: chex.PRNGKey) → evorl.types.State

Initialize the state of the .

This is the public API to call for instance state initialization.

abstract learn(state: evorl.types.State) → evorl.types.State

Run the complete learning process.

The learning process includes:

• call multiple times of step()

• record the metrics

• save checkpoints

abstract setup(key: chex.PRNGKey) → evorl.types.State