evorl.algorithms.meta.pbt_ppo.pbt_cso_param_ppo

Module Contents

Classes

API

class evorl.algorithms.meta.pbt_ppo.pbt_cso_param_ppo.PBTCSOOptState[source]

Bases: evorl.algorithms.meta.pbt_workflow.PBTOptState

velocity: chex.ArrayTree

None

class evorl.algorithms.meta.pbt_ppo.pbt_cso_param_ppo.PBTCSOParamPPOWorkflow(workflow: evorl.workflows.RLWorkflow, evaluator: evorl.evaluators.Evaluator, config: omegaconf.DictConfig)[source]

Bases: evorl.algorithms.meta.pbt_ppo.pbt_param_ppo.PBTParamPPOWorkflow

exploit_and_explore(pbt_opt_state: evorl.algorithms.meta.pbt_workflow.PBTOptState, pop: chex.ArrayTree, pop_workflow_state: evorl.types.State, pop_metrics: chex.ArrayTree, key: chex.PRNGKey) tuple[chex.ArrayTree, evorl.types.State, evorl.algorithms.meta.pbt_workflow.PBTOptState][source]
classmethod name()[source]