lit_sb3.algorithms.tqc

source package lit_sb3.algorithms.tqc

Classes

• Actor — Actor network (policy) for TQC.

• CnnPolicy — Policy class (with both actor and critic) for TQC.

• Critic — Critic network (q-value function) for TQC.

• MultiInputPolicy — Policy class (with both actor and critic) for TQC.

• TQC — Controlling Overestimation Bias with Truncated Mixture of Continuous.

• TQCPolicy — Policy class (with both actor and critic) for TQC.

source class Actor(observation_space: spaces.Space, action_space: spaces.Box, net_arch: list[int], features_extractor: nn.Module, features_dim: int, activation_fn: type[nn.Module] = nn.ReLU, use_sde: bool = False, log_std_init: float = -3, full_std: bool = True, use_expln: bool = False, clip_mean: float = 2.0, normalize_images: bool = True)

Bases : BasePolicy

Actor network (policy) for TQC.

Parameters

• observation_space : spaces.Space — Obervation space

• action_space : spaces.Box — Action space

• net_arch : list[int] — Network architecture

• features_extractor : nn.Module — Network to extract features (a CNN when using images, a nn.Flatten() layer otherwise)

• features_dim : int — Number of features

• activation_fn : type[nn.Module] — Activation function

• use_sde : bool — Whether to use State Dependent Exploration or not

• log_std_init : float — Initial value for the log standard deviation

• full_std : bool — Whether to use (n_features x n_actions) parameters for the std instead of only (n_features,) when using gSDE.

• use_expln : bool — Use expln() function instead of exp() when using gSDE to ensure a positive standard deviation (cf paper). It allows to keep variance above zero and prevent it from growing too fast. In practice, exp() is usually enough.

• clip_mean : float — Clip the mean output when using gSDE to avoid numerical instability.

• normalize_images : bool — Whether to normalize images or not, dividing by 255.0 (True by default)

Attributes

• device : torch.device — Infer which device this policy lives on by inspecting its parameters.

• squash_output : bool — (bool) Getter for squash_output.

Methods

• get_std — Retrieve the standard deviation of the action distribution.

• reset_noise — Sample new weights for the exploration matrix, when using gSDE.

• get_action_dist_params — Get the parameters for the action distribution.

• forward

• action_log_prob

source method Actor.get_std() → torch.Tensor

Retrieve the standard deviation of the action distribution.

Only useful when using gSDE. It corresponds to torch.exp(log_std) in the normal case, but is slightly different when using expln function (cf StateDependentNoiseDistribution doc).

source method Actor.reset_noise(batch_size: int = 1) → None

Sample new weights for the exploration matrix, when using gSDE.

Parameters

• batch_size : int

• batch_size : int — The number of samples in the batch.

source method Actor.get_action_dist_params(obs: PyTorchObs) → tuple[torch.Tensor, torch.Tensor, dict[str, torch.Tensor]]

Get the parameters for the action distribution.

Parameters

• obs : PyTorchObs

• obs : PyTorchObs — The current observation.

Returns

• tuple[torch.Tensor, torch.Tensor, dict[str, torch.Tensor]] — Mean, standard deviation and optional keyword arguments.

source method Actor.forward(obs: PyTorchObs, deterministic: bool = False) → torch.Tensor

source method Actor.action_log_prob(obs: PyTorchObs) → tuple[torch.Tensor, torch.Tensor]

source class CnnPolicy(observation_space: spaces.Space, action_space: spaces.Box, lr_schedule: Schedule, net_arch: list[int] | dict[str, list[int]] | None = None, activation_fn: type[nn.Module] = nn.ReLU, use_sde: bool = False, log_std_init: float = -3, use_expln: bool = False, clip_mean: float = 2.0, features_extractor_class: type[BaseFeaturesExtractor] = NatureCNN, features_extractor_kwargs: dict[str, Any] | None = None, normalize_images: bool = True, optimizer_class: type[torch.optim.Optimizer] = torch.optim.Adam, optimizer_kwargs: dict[str, Any] | None = None, n_quantiles: int = 25, n_critics: int = 2, share_features_extractor: bool = False)

Bases : TQCPolicy

Policy class (with both actor and critic) for TQC.

Parameters

• observation_space : spaces.Space — Observation space

• action_space : spaces.Box — Action space

• lr_schedule : Schedule — Learning rate schedule (could be constant)

• net_arch : list[int] | dict[str, list[int]] | None — The specification of the policy and value networks.

• activation_fn : type[nn.Module] — Activation function

• use_sde : bool — Whether to use State Dependent Exploration or not

• log_std_init : float — Initial value for the log standard deviation

• use_expln : bool — Use expln() function instead of exp() when using gSDE to ensure a positive standard deviation (cf paper). It allows to keep variance above zero and prevent it from growing too fast. In practice, exp() is usually enough.

• clip_mean : float — Clip the mean output when using gSDE to avoid numerical instability.

• features_extractor_class : type[BaseFeaturesExtractor] — Features extractor to use.

• normalize_images : bool — Whether to normalize images or not, dividing by 255.0 (True by default)

• optimizer_class : type[torch.optim.Optimizer] — The optimizer to use, torch.optim.Adam by default

• optimizer_kwargs : dict[str, Any] | None — Additional keyword arguments, excluding the learning rate, to pass to the optimizer

• n_quantiles : int — Number of quantiles for the critic.

• n_critics : int — Number of critic networks to create.

• share_features_extractor : bool — Whether to share or not the features extractor between the actor and the critic (this saves computation time)

Attributes

• device : torch.device — Infer which device this policy lives on by inspecting its parameters.

• squash_output : bool — (bool) Getter for squash_output.

source class Critic(observation_space: spaces.Space, action_space: spaces.Box, net_arch: list[int], features_extractor: BaseFeaturesExtractor, features_dim: int, activation_fn: type[nn.Module] = nn.ReLU, normalize_images: bool = True, n_quantiles: int = 25, n_critics: int = 2, share_features_extractor: bool = False)

Bases : BaseModel

Critic network (q-value function) for TQC.

Parameters

• observation_space : spaces.Space — Obervation space

• action_space : spaces.Box — Action space

• net_arch : list[int] — Network architecture

• features_extractor : BaseFeaturesExtractor — Network to extract features (a CNN when using images, a nn.Flatten() layer otherwise)

• features_dim : int — Number of features

• activation_fn : type[nn.Module] — Activation function

• normalize_images : bool — Whether to normalize images or not, dividing by 255.0 (True by default)

• share_features_extractor : bool — Whether the features extractor is shared or not between the actor and the critic (this saves computation time)

Attributes

• device : torch.device — Infer which device this policy lives on by inspecting its parameters.

Methods

• forward

source method Critic.forward(obs: PyTorchObs, action: torch.Tensor) → torch.Tensor

source class MultiInputPolicy(observation_space: spaces.Space, action_space: spaces.Box, lr_schedule: Schedule, net_arch: list[int] | dict[str, list[int]] | None = None, activation_fn: type[nn.Module] = nn.ReLU, use_sde: bool = False, log_std_init: float = -3, use_expln: bool = False, clip_mean: float = 2.0, features_extractor_class: type[BaseFeaturesExtractor] = CombinedExtractor, features_extractor_kwargs: dict[str, Any] | None = None, normalize_images: bool = True, optimizer_class: type[torch.optim.Optimizer] = torch.optim.Adam, optimizer_kwargs: dict[str, Any] | None = None, n_quantiles: int = 25, n_critics: int = 2, share_features_extractor: bool = False)

Bases : TQCPolicy

Policy class (with both actor and critic) for TQC.

Parameters

• observation_space : spaces.Space — Observation space

• action_space : spaces.Box — Action space

• lr_schedule : Schedule — Learning rate schedule (could be constant)

• net_arch : list[int] | dict[str, list[int]] | None — The specification of the policy and value networks.

• activation_fn : type[nn.Module] — Activation function

• use_sde : bool — Whether to use State Dependent Exploration or not

• log_std_init : float — Initial value for the log standard deviation

• use_expln : bool — Use expln() function instead of exp() when using gSDE to ensure a positive standard deviation (cf paper). It allows to keep variance above zero and prevent it from growing too fast. In practice, exp() is usually enough.

• clip_mean : float — Clip the mean output when using gSDE to avoid numerical instability.

• features_extractor_class : type[BaseFeaturesExtractor] — Features extractor to use.

• normalize_images : bool — Whether to normalize images or not, dividing by 255.0 (True by default)

• optimizer_class : type[torch.optim.Optimizer] — The optimizer to use, torch.optim.Adam by default

• optimizer_kwargs : dict[str, Any] | None — Additional keyword arguments, excluding the learning rate, to pass to the optimizer

• n_quantiles : int — Number of quantiles for the critic.

• n_critics : int — Number of critic networks to create.

• share_features_extractor : bool — Whether to share or not the features extractor between the actor and the critic (this saves computation time)

Attributes

• device : torch.device — Infer which device this policy lives on by inspecting its parameters.

• squash_output : bool — (bool) Getter for squash_output.

source class TQC(policy: str | type[TQCPolicy], learning_rate: float = 0.0003, buffer_size: int = 1000000, learning_starts: int = 100, batch_size: int = 256, tau: float = 0.005, gamma: float = 0.99, train_freq: int | tuple[int, str] = 1, gradient_steps: int = 1, action_noise: ActionNoise | None = None, replay_buffer_class: type[ReplayBuffer] | None = None, replay_buffer_kwargs: dict[str, Any] | None = None, optimize_memory_usage: bool = False, n_steps: int = 1, ent_coef: str | float = 'auto', target_update_interval: int = 1, target_entropy: str | float = 'auto', top_quantiles_to_drop_per_net: int = 2, use_sde: bool = False, sde_sample_freq: int = -1, use_sde_at_warmup: bool = False, stats_window_size: int = 100, policy_kwargs: dict[str, Any] | None = None, verbose: int = 0, seed: int | None = None, device: torch.device | str = 'auto', _init_setup_model: bool = True)

Bases : OffPolicyAlgorithm

Controlling Overestimation Bias with Truncated Mixture of Continuous.

Distributional Quantile Critics (TQC).

Paper: https://arxiv.org/abs/2005.04269 This implementation adapts TQC from sb3-contrib to use PyTorch Lightning.

Attributes

• device : torch.device — Return current device (Lightning-aware).

• hparams : Union[AttributeDict, MutableMapping] — meth:save_hyperparameters. It is mutable by the user. For the frozen set of initial hyperparameters, use :attr:hparams_initial.

• hparams_initial : AttributeDict — meth:save_hyperparameters. These contents are read-only. Manual updates to the saved hyperparameters can instead be performed through :attr:hparams.

• example_input_array : Optional[Union[Tensor, tuple, dict]] — meth:forward method. The return type is interpreted as follows:

• current_epoch : int — The current epoch in the Trainer, or 0 if not attached.

• global_step : int — Total training batches seen across all epochs.

• global_rank : int — The index of the current process across all nodes and devices.

• local_rank : int — The index of the current process within a single node.

• on_gpu : bool — Returns True if this model is currently located on a GPU.

• strict_loading : bool — Determines how Lightning loads this model using .load_state_dict(..., strict=model.strict_loading).

• logger : Optional[Union[Logger, FabricLogger]] — Reference to the logger object in the Trainer.

• loggers : Union[list[Logger], list[FabricLogger]] — Reference to the list of loggers in the Trainer.

• device_mesh : Optional['DeviceMesh'] — Strategies like ModelParallelStrategy will create a device mesh that can be accessed in the :meth:~lightning.pytorch.core.hooks.ModelHooks.configure_model hook to parallelize the LightningModule.

• env : VecEnv | None — Return the active training env from the trainer, or None.

Methods

• configure_optimizers

• training_step — Off-policy TQC step: collect env transitions then do gradient updates.

• learn

source method TQC.configure_optimizers() → OptimizerLRScheduler

source method TQC.training_step(batch: Any, batch_idx: int) → None

Off-policy TQC step: collect env transitions then do gradient updates.

source method TQC.learn(total_timesteps: int, env: GymEnv | str | None = None, callback: MaybeCallback = None, log_every_n_steps: int | None = 4, tb_log_name: str = 'TQC', reset_num_timesteps: bool = True, progress_bar: bool = False) → SelfTQC

source class TQCPolicy(observation_space: spaces.Space, action_space: spaces.Box, lr_schedule: Schedule, net_arch: list[int] | dict[str, list[int]] | None = None, activation_fn: type[nn.Module] = nn.ReLU, use_sde: bool = False, log_std_init: float = -3, use_expln: bool = False, clip_mean: float = 2.0, features_extractor_class: type[BaseFeaturesExtractor] = FlattenExtractor, features_extractor_kwargs: dict[str, Any] | None = None, normalize_images: bool = True, optimizer_class: type[torch.optim.Optimizer] = torch.optim.Adam, optimizer_kwargs: dict[str, Any] | None = None, n_quantiles: int = 25, n_critics: int = 2, share_features_extractor: bool = False)

Bases : BasePolicy

Policy class (with both actor and critic) for TQC.

Parameters

• observation_space : spaces.Space — Observation space

• action_space : spaces.Box — Action space

• lr_schedule : Schedule — Learning rate schedule (could be constant)

• net_arch : list[int] | dict[str, list[int]] | None — The specification of the policy and value networks.

• activation_fn : type[nn.Module] — Activation function

• use_sde : bool — Whether to use State Dependent Exploration or not

• log_std_init : float — Initial value for the log standard deviation

• use_expln : bool — Use expln() function instead of exp() when using gSDE to ensure a positive standard deviation (cf paper). It allows to keep variance above zero and prevent it from growing too fast. In practice, exp() is usually enough.

• clip_mean : float — Clip the mean output when using gSDE to avoid numerical instability.

• features_extractor_class : type[BaseFeaturesExtractor] — Features extractor to use.

• features_extractor_kwargs : dict[str, Any] | None — Keyword arguments to pass to the feature extractor.

• normalize_images : bool — Whether to normalize images or not, dividing by 255.0 (True by default)

• optimizer_class : type[torch.optim.Optimizer] — The optimizer to use, torch.optim.Adam by default

• optimizer_kwargs : dict[str, Any] | None — Additional keyword arguments, excluding the learning rate, to pass to the optimizer

• n_quantiles : int — Number of quantiles for the critic.

• n_critics : int — Number of critic networks to create.

• share_features_extractor : bool — Whether to share or not the features extractor between the actor and the critic (this saves computation time)

Attributes

• device : torch.device — Infer which device this policy lives on by inspecting its parameters.

• squash_output : bool — (bool) Getter for squash_output.

Methods

• reset_noise — Sample new weights for the exploration matrix, when using gSDE.

• make_actor

• make_critic

• forward

• set_training_mode — Put the policy in either training or evaluation mode.

source method TQCPolicy.reset_noise(batch_size: int = 1) → None

Sample new weights for the exploration matrix, when using gSDE.

Parameters

• batch_size : int

• batch_size : int — The number of samples in the batch.

source method TQCPolicy.make_actor(features_extractor: BaseFeaturesExtractor | None = None) → Actor

source method TQCPolicy.make_critic(features_extractor: BaseFeaturesExtractor | None = None) → Critic

source method TQCPolicy.forward(obs: PyTorchObs, deterministic: bool = False) → torch.Tensor

source method TQCPolicy.set_training_mode(mode: bool) → None

Put the policy in either training or evaluation mode.

This affects certain modules, such as batch normalisation and dropout.

Parameters

• mode : bool — if true, set to training mode, else set to evaluation mode