`evorl.algorithms.ec.so.es_workflow`¶

Module Contents¶

Classes¶

ESWorkflowTemplate

API¶

class evorl.algorithms.ec.so.es_workflow.ESWorkflowTemplate(*, env: evorl.envs.Env, agent: evorl.agent.Agent, ec_optimizer: evorl.ec.optimizers.EvoOptimizer, ec_evaluator: evorl.evaluators.Evaluator, evaluator: evorl.evaluators.Evaluator, agent_state_vmap_axes: evorl.agent.AgentStateAxis = 0, config: omegaconf.DictConfig)[source]¶

Bases: evorl.workflows.ECWorkflowTemplate

classmethod enable_jit() → None[source]¶

classmethod enable_shmap(axis_name) → None[source]¶

evaluate(state: evorl.types.State) → tuple[evorl.metrics.MetricBase, evorl.types.State][source]¶: Evaluate the policy with the mean of ES.

learn(state: evorl.types.State) → evorl.types.State[source]¶