Parallel runner¶
-
class
tensorforce.execution.
ParallelRunner
(agent, environment=None, num_parallel=None, environments=None, max_episode_timesteps=None, evaluation_environment=None, save_best_agent=None)[source]¶ Tensorforce parallel runner utility.
Parameters: - agent (specification | Agent object) – Agent specification or object, the latter is not
closed automatically as part of
runner.close()
(required). - environment (specification | Environment object) – Environment specification or object, the
latter is not closed automatically as part of
runner.close()
(required, or alternativelyenvironments
). - num_parallel (int > 0) – Number of parallel environment instances to run
(required, or alternatively
environments
). - environments (list[specification | Environment object]) – Environment specifications or
objects, the latter are not closed automatically as part of
runner.close()
(required, or alternativelyenvironment
andnum_parallel
). - max_episode_timesteps (int > 0) – Maximum number of timesteps per episode, overwrites the environment default if defined (default: environment default).
- evaluation_environment (specification | Environment object) – Evaluation environment or
object, the latter is not closed automatically as part of
runner.close()
(default: none). - save_best_agent (string) – Directory to save the best version of the agent according to the evaluation (default: best agent is not saved).
- agent (specification | Agent object) – Agent specification or object, the latter is not
closed automatically as part of