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]¶