Exemplos de KLCoeffMixin.__init__ em Python

Exemplo n.º 1

def setup_mixins(policy, obs_space, action_space, config):
    ValueNetworkMixin.__init__(policy, obs_space, action_space, config)
    KLCoeffMixin.__init__(policy, config)
    EntropyCoeffSchedule.__init__(policy, config["entropy_coeff"],
                                  config["entropy_coeff_schedule"])
    LearningRateSchedule.__init__(policy, config["lr"], config["lr_schedule"])
    AddMaskInfoMixinForPolicy.__init__(policy)

Exemplo n.º 2

Arquivo: ppo_moa.py Projeto: Matsunaga-D/sequential_social_dilemma_games_paper_code

def setup_ppo_moa_mixins(policy, obs_space, action_space, config):
    """
    Calls init on all PPO+MOA mixins in the policy
    """
    ValueNetworkMixin.__init__(policy, obs_space, action_space, config)
    KLCoeffMixin.__init__(policy, config)
    EntropyCoeffSchedule.__init__(policy, config["entropy_coeff"],
                                  config["entropy_coeff_schedule"])
    LearningRateSchedule.__init__(policy, config["lr"], config["lr_schedule"])
    setup_moa_mixins(policy, obs_space, action_space, config)

Exemplo n.º 3

def setup_mixins(policy, obs_space, action_space, config):
    # copied from PPO
    KLCoeffMixin.__init__(policy, config)
    EntropyCoeffSchedule.__init__(policy, config["entropy_coeff"],
                                  config["entropy_coeff_schedule"])
    warmup_steps = config["model"]["custom_model_config"].get(
        "warmup_steps", 100000)
    TransformerLearningRateSchedule.__init__(
        policy, config["model"]["custom_model_config"]["critic"]["d_model"],
        warmup_steps)

Exemplo n.º 4

Arquivo: appo_tf_policy.py Projeto: zivzone/ray

def setup_mixins(policy: Policy, obs_space: gym.spaces.Space,
                 action_space: gym.spaces.Space,
                 config: TrainerConfigDict) -> None:
    """Call all mixin classes' constructors before APPOPolicy initialization.

    Args:
        policy (Policy): The Policy object.
        obs_space (gym.spaces.Space): The Policy's observation space.
        action_space (gym.spaces.Space): The Policy's action space.
        config (TrainerConfigDict): The Policy's config.
    """
    LearningRateSchedule.__init__(policy, config["lr"], config["lr_schedule"])
    KLCoeffMixin.__init__(policy, config)
    ValueNetworkMixin.__init__(policy, obs_space, action_space, config)

Exemplo n.º 5

def setup_mixins(policy, obs_space, action_space, config):
    # copied from PPO
    KLCoeffMixin.__init__(policy, config)
    EntropyCoeffSchedule.__init__(policy, config["entropy_coeff"],
                                  config["entropy_coeff_schedule"])
    LearningRateSchedule.__init__(policy, config["lr"], config["lr_schedule"])

Exemplo n.º 6

def setup_mixins(policy, obs_space, action_space, config):
    LearningRateSchedule.__init__(policy, config["lr"], config["lr_schedule"])
    KLCoeffMixin.__init__(policy, config)
    ValueNetworkMixin.__init__(policy, obs_space, action_space, config)

Exemplo n.º 7

def setup_tf_mixins(policy, obs_space, action_space, config):
    # Copied from PPOTFPolicy (w/o ValueNetworkMixin).
    KLCoeffMixin.__init__(policy, config)
    EntropyCoeffSchedule.__init__(policy, config["entropy_coeff"],
                                  config["entropy_coeff_schedule"])
    LearningRateSchedule.__init__(policy, config["lr"], config["lr_schedule"])