Python learner_loopの例

コード例 #1

def main(argv):
    if len(argv) > 1:
        raise app.UsageError('Too many command-line arguments.')
    if FLAGS.run_mode == 'actor':
        actor.actor_loop(env.create_environment)
    elif FLAGS.run_mode == 'learner':
        learner.learner_loop(env.create_environment, create_agent,
                             create_optimizer)
    else:
        raise ValueError('Unsupported run mode {}'.format(FLAGS.run_mode))

コード例 #2

def main(argv):
    fps_log = Logger('fps.log', level='info')
    if len(argv) > 1:
        raise app.UsageError('Too many command-line arguments.')
    if FLAGS.run_mode == 'actor':
        actor.actor_loop(create_atari_env)
    elif FLAGS.run_mode == 'learner':
        learner.learner_loop(create_atari_env, create_agent, create_optimizer,
                             fps_log)
    else:
        raise ValueError('Unsupported run mode {}'.format(FLAGS.run_mode))

コード例 #3

ファイル: vtrace_main.py プロジェクト: zerocurve/seed_rl

def main(argv):
  create_environment = lambda task, config: env.create_environment(  
      env_name=config.env_name,
      discretization=config.discretization,
      n_actions_per_dim=config.n_actions_per_dim,
      action_ratio=config.action_ratio)

  if len(argv) > 1:
    raise app.UsageError('Too many command-line arguments.')
  if FLAGS.run_mode == 'actor':
    actor.actor_loop(create_environment)
  elif FLAGS.run_mode == 'learner':
    learner.learner_loop(create_environment,
                         create_agent,
                         create_optimizer)
  else:
    raise ValueError('Unsupported run mode {}'.format(FLAGS.run_mode))

コード例 #4

ファイル: vtrace_main.py プロジェクト: do-not-be-hasty/seed_rl

def main(argv):
    if len(argv) > 1:
        raise app.UsageError('Too many command-line arguments.')
    if FLAGS.run_mode == 'actor':
        actor.actor_loop(env.create_environment)
    elif FLAGS.run_mode == 'learner':
        neptune.init('do-not-be-hasty/matrace')
        neptune.create_experiment(tags=[FLAGS.nonce])
        neptune_tensorboard.integrate_with_tensorflow()

        learner.learner_loop(env.create_environment, create_agent,
                             create_optimizer)
    elif FLAGS.run_mode == 'visualize':
        visualize.visualize(env.create_environment, create_agent,
                            create_optimizer)
    else:
        raise ValueError('Unsupported run mode {}'.format(FLAGS.run_mode))

コード例 #5

ファイル: vtrace_better_main.py プロジェクト: do-not-be-hasty/seed_rl

def main(argv):
    if len(argv) > 1:
        raise app.UsageError('Too many command-line arguments.')
    if FLAGS.run_mode == 'actor':
        if not FLAGS.is_local:
            get_configuration(config_file=FLAGS.mrunner_config,
                              inject_parameters_to_FLAGS=True)
        actor.actor_loop(env.create_environment)
    elif FLAGS.run_mode == 'learner':
        if not FLAGS.is_local:
            get_configuration(config_file=FLAGS.mrunner_config,
                              print_diagnostics=True,
                              with_neptune=True,
                              inject_parameters_to_FLAGS=True)
            experiment = neptune.get_experiment()
            experiment.append_tag(tag=FLAGS.nonce)
            neptune_tensorboard.integrate_with_tensorflow()
        learner.learner_loop(env.create_environment, create_agent,
                             create_optimizer)
    elif FLAGS.run_mode == 'visualize':
        visualize.visualize(env.create_environment, create_agent,
                            create_optimizer)
    else:
        raise ValueError('Unsupported run mode {}'.format(FLAGS.run_mode))