Parallelization¶
This page contains the reference documentation for the parallelization module.
Observation aggregator used in distributed training for aggregating observations of multiple instances of the same environment. |
|
This class holds a policy as well an env in order to step through the env, by producing action from the policy and recoding the rollout to be processed by the learner. |
|
Base class for outputs generated by the agent. |
Distributed Environments¶
These are interfaces, classes and utility functions for distributed environments:
Abstract base class for distributed environments. |
|
Creates a simple wrapper for multiple environments, calling each environment in sequence on the current Python process. |
Distributed Actors¶
These are interfaces, classes and utility functions for distributed actors:
Steps through a given environment and records rollouts. |
|
The base class for all distributed actors. |