`evorl.algorithms.erl.erl_td3.erl_es`¶

Module Contents¶

Classes¶

`ERLESWorkflow`	ERL w/ ES.
`EvaluateMetric`

API¶

class evorl.algorithms.erl.erl_td3.erl_es.ERLESWorkflow(**kwargs)[source]¶

Bases: evorl.algorithms.erl.erl_td3.erl_td3_workflow.ERLTD3WorkflowTemplate

ERL w/ ES.

Configs:

EC: n actors
RL: k actors + k critics
Shared replay buffer

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

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

classmethod name()[source]¶

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

class evorl.algorithms.erl.erl_td3.erl_es.EvaluateMetric[source]¶

Bases: evorl.metrics.MetricBase

pop_center_episode_lengths: chex.Array¶: None

pop_center_episode_returns: chex.Array¶: None

rl_episode_lengths: chex.Array¶: None

rl_episode_returns: chex.Array¶: None