evorl.algorithms.contrib.td3_v2¶
Module Contents¶
Classes¶
The similar impl of TD3 in SB3 and CleanRL. |
Data¶
API¶
- evorl.algorithms.contrib.td3_v2.MISSING_LOSS¶
None
- class evorl.algorithms.contrib.td3_v2.TD3V2Workflow(env: evorl.envs.Env, agent: evorl.agent.Agent, optimizer: optax.GradientTransformation, evaluator: evorl.evaluators.Evaluator, replay_buffer: evorl.replay_buffers.AbstractReplayBuffer, config: omegaconf.DictConfig)[source]¶
Bases:
evorl.algorithms.td3.TD3WorkflowThe similar impl of TD3 in SB3 and CleanRL.
- learn(state: evorl.types.State) evorl.types.State[source]¶
- step(state: evorl.types.State) tuple[evorl.metrics.MetricBase, evorl.types.State][source]¶