garage.tf.samplers package¶
Samplers which run agents that use Tensorflow in environments.
-
class
BatchSampler
(algo, env, n_envs)[source]¶ Bases:
garage.sampler.sampler_deprecated.BaseSampler
Collects samples in parallel using a stateful pool of workers.
Parameters: - algo (garage.np.algos.RLAlgorithm) – The algorithm.
- env (gym.Env) – The environment.
- n_envs (int) – Number of environments.
-
class
TFWorkerClassWrapper
(wrapped_class)[source]¶ Bases:
object
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 garage.sampler.Worker.
-
class
TFWorkerWrapper
[source]¶ Bases:
garage.sampler.worker.Worker
Wrapper around another workers that initializes a TensorFlow Session.
-
agent
¶ Returns the worker’s agent.
Returns: the worker’s agent. Return type: garage.Policy
-
collect_rollout
()[source]¶ Collect the current rollout, clearing the internal buffer.
Returns: - Batch of sampled trajectories. May be
- truncated if the rollouts haven’t completed yet.
Return type: garage.TrajectoryBatch
-
env
¶ Returns the worker’s environment.
Returns: the worker’s environment. Return type: gym.Env
-
rollout
()[source]¶ Sample a single rollout of the agent in the environment.
Returns: - Batch of sampled trajectories. May be
- truncated if max_path_length is set.
Return type: garage.TrajectoryBatch
-
step_rollout
()[source]¶ Take a single time-step in the current rollout.
Returns: - True iff the path is done, either due to the environment
- indicating termination of due to reaching max_path_length.
Return type: bool
-
update_agent
(agent_update)[source]¶ 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.
-