`evorl.algorithms.random_agent`¶

Module Contents¶

Classes¶

`RandomAgentWorkflow`
`RandomTrainMetric`

API¶

class evorl.algorithms.random_agent.RandomAgentWorkflow(agent: evorl.agent.Agent, evaluator: evorl.evaluators.Evaluator, config: omegaconf.DictConfig)[source]¶

Bases: evorl.workflows.RLWorkflow

evaluate(state: evorl.types.State) → tuple[evorl.metrics.MetricBase, evorl.types.State][source]¶

learn(state: evorl.types.State) → evorl.types.State[source]¶: Dummy learn function for random agent.

classmethod name()[source]¶

setup(key: chex.PRNGKey) → evorl.types.State[source]¶

step(state: evorl.types.State) → tuple[evorl.metrics.MetricBase, evorl.types.State][source]¶: Dummy step function for random agent.

class evorl.algorithms.random_agent.RandomTrainMetric[source]¶: Bases: evorl.metrics.MetricBase