pytorch_trainer

Module pytorch_multi_process_trainer. Specifies a trainer for PyTorch-based models.

pytorch_trainer.worker(worker_idx: int, worker_model: Module, params: dir)

Executes the process work

Parameters

  • worker_idx (The id of the worker) –

  • worker_model (The model the worker is using) –

  • params (Parameters needed) –

class pytorch_trainer.PyTorchTrainerConfig(n_procs: int = 1, n_episodes: int = 100)

Configuration for PyTorchMultiProcessTrainer

class pytorch_trainer.PyTorchTrainer(env: Env, agent: Agent, config: PyTorchTrainerConfig)

The class PyTorchMultiProcessTrainer. Trainer for multiprocessing with PyTorch

__init__(env: Env, agent: Agent, config: PyTorchTrainerConfig) → None

Constructor. Initialize a trainer by passing the training environment instance the agent to train and configuration dictionary

Parameters

  • agent (The agent to train) –

  • config (Configuration parameters for the trainer) –

actions_after_episode_ends(env: Env, episode_idx: int, **options) → None

Any actions after the training episode ends

Parameters

  • env (The environment to train on) –

  • episode_idx (The training episode index) –

  • options (Any options passed by the client code) –

Return type

None

actions_before_episode_begins(env: Env, episode_idx: int, **options) → None

Perform any actions necessary before the training begins

Parameters

  • env (The environment to train on) –

  • episode_idx (The training episode index) –

  • options (Any options passed by the client code) –

Return type

None

actions_before_training() → None

Any actions to perform before training begins

Return type

None

avg_distortion() → array

Returns the average reward per episode :return:

avg_rewards() → array

Returns the average reward per episode :return: