evorl.algorithms.erl.cemrl_td3.cemrl_openes

Module Contents

Classes

CEMRLOpenESWorkflow

1 critic + n actors + 1 replay buffer.

API

class evorl.algorithms.erl.cemrl_td3.cemrl_openes.CEMRLOpenESWorkflow(**kwargs)

Bases: evorl.algorithms.erl.cemrl_td3.cemrl_td3_workflow.CEMRLTD3WorkflowTemplate

1 critic + n actors + 1 replay buffer.

We use shard_map to split and parallel the population.

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

classmethod name()

step(state: evorl.types.State) → tuple[evorl.metrics.MetricBase, evorl.types.State]