hive.runners.single_agent_loop module

class hive.runners.single_agent_loop.SingleAgentRunner(environment, agent, logger, experiment_manager, train_steps, test_frequency, test_episodes, stack_size, max_steps_per_episode=27000)

Bases: hive.runners.base.Runner

Runner class used to implement a sinle-agent training loop.

Initializes the Runner object.

Parameters

• environment (BaseEnv) – Environment used in the training loop.

• agent (Agent) – Agent that will interact with the environment

• logger (ScheduledLogger) – Logger object used to log metrics.

• experiment_manager (Experiment) – Experiment object that saves the state of the training.

• train_steps (int) – How many steps to train for. If this is -1, there is no limit for the number of training steps.

• test_frequency (int) – After how many training steps to run testing episodes. If this is -1, testing is not run.

• test_episodes (int) – How many episodes to run testing for duing each test phase.

• stack_size (int) – The number of frames in an observation sent to an agent.

• max_steps_per_episode (int) – The maximum number of steps to run an episode for.

run_one_step(observation, episode_metrics)

Run one step of the training loop.

Parameters

• observation – Current observation that the agent should create an action for.

• episode_metrics (Metrics) – Keeps track of metrics for current episode.

run_episode()

Run a single episode of the environment.

hive.runners.single_agent_loop.set_up_experiment(config)

Returns a SingleAgentRunner object based on the config and any command line arguments.

Parameters

config – Configuration for experiment.

hive.runners.single_agent_loop.main()