src/algos/no_episodic_counts.py [231:277]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
        learner_model = MinigridPolicyNet(env.observation_space.shape, env.action_space.n)\
            .to(device=flags.device)
    else:
        learner_model = MarioDoomPolicyNet(env.observation_space.shape, env.action_space.n)\
            .to(device=flags.device)

    optimizer = torch.optim.RMSprop(
        learner_model.parameters(),
        lr=flags.learning_rate,
        momentum=flags.momentum,
        eps=flags.epsilon,
        alpha=flags.alpha)
    
    state_embedding_optimizer = torch.optim.RMSprop(
        state_embedding_model.parameters(),
        lr=flags.learning_rate,
        momentum=flags.momentum,
        eps=flags.epsilon,
        alpha=flags.alpha)
    
    inverse_dynamics_optimizer = torch.optim.RMSprop(
        inverse_dynamics_model.parameters(),
        lr=flags.learning_rate,
        momentum=flags.momentum,
        eps=flags.epsilon,
        alpha=flags.alpha)
    
    forward_dynamics_optimizer = torch.optim.RMSprop(
        forward_dynamics_model.parameters(),
        lr=flags.learning_rate,
        momentum=flags.momentum,
        eps=flags.epsilon,
        alpha=flags.alpha)
    
    
    def lr_lambda(epoch):
        return 1 - min(epoch * T * B, flags.total_frames) / flags.total_frames

    scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda)

    logger = logging.getLogger('logfile')
    stat_keys = [
        'total_loss',
        'mean_episode_return',
        'pg_loss',
        'baseline_loss',
        'entropy_loss',
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -



src/algos/ride.py [250:296]:
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -
            learner_model = MinigridPolicyNet(env.observation_space.shape, env.action_space.n)\
                .to(device=flags.device)
    else:
        learner_model = MarioDoomPolicyNet(env.observation_space.shape, env.action_space.n)\
            .to(device=flags.device)

    optimizer = torch.optim.RMSprop(
        learner_model.parameters(),
        lr=flags.learning_rate,
        momentum=flags.momentum,
        eps=flags.epsilon,
        alpha=flags.alpha)

    state_embedding_optimizer = torch.optim.RMSprop(
        state_embedding_model.parameters(),
        lr=flags.learning_rate,
        momentum=flags.momentum,
        eps=flags.epsilon,
        alpha=flags.alpha)
    
    inverse_dynamics_optimizer = torch.optim.RMSprop(
        inverse_dynamics_model.parameters(),
        lr=flags.learning_rate,
        momentum=flags.momentum,
        eps=flags.epsilon,
        alpha=flags.alpha)
    
    forward_dynamics_optimizer = torch.optim.RMSprop(
        forward_dynamics_model.parameters(),
        lr=flags.learning_rate,
        momentum=flags.momentum,
        eps=flags.epsilon,
        alpha=flags.alpha)
        

    def lr_lambda(epoch):
        return 1 - min(epoch * T * B, flags.total_frames) / flags.total_frames

    scheduler = torch.optim.lr_scheduler.LambdaLR(optimizer, lr_lambda)

    logger = logging.getLogger('logfile')
    stat_keys = [
        'total_loss',
        'mean_episode_return',
        'pg_loss',
        'baseline_loss',
        'entropy_loss',
- - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - - -