garage.tf.samplers.worker
¶
Default TensorFlow sampler Worker.
- class TFWorkerClassWrapper(wrapped_class)¶
Acts like a Worker class, but is actually an object.
When called, constructs the wrapped class and wraps it in a
TFWorkerWrapper
.- Parameters
wrapped_class (type) – The class to wrap. Should be a subclass of
Worker
.
- class TFWorkerWrapper¶
Bases:
garage.sampler.worker.Worker
Wrapper around another workers that initializes a TensorFlow Session.
- property env¶
Worker’s environment.
- Type
- worker_init()¶
Initialize a worker.
- shutdown()¶
Perform shutdown processes for TF.
- update_agent(agent_update)¶
Update the worker’s agent, using agent_update.
- Parameters
agent_update (object) – An agent update. The exact type of this argument depends on the
Worker
implementation.
- update_env(env_update)¶
Update the worker’s env, using env_update.
- Parameters
env_update (object) – An environment update. The exact type of this argument depends on the
Worker
implementation.
- rollout()¶
Sample a single episode of the agent in the environment.
- Returns
- Batch of sampled episodes. May be truncated if
max_episode_length is set.
- Return type
- start_episode()¶
Begin a new episode.
- step_episode()¶
Take a single time-step in the current episode.
- Returns
- True iff the episode is done, either due to the environment
indicating termination of due to reaching max_episode_length.
- Return type
- collect_episode()¶
Collect the current episode, clearing the internal buffer.
- Returns
- Batch of sampled episodes. May be truncated if the
episodes haven’t completed yet.
- Return type