Struct Iqn 

pub struct Iqn<E, F, M, R>
where
    F: SubModel<Output = Tensor>,
    M: SubModel<Input = Tensor, Output = Tensor>,
    F::Config: DeserializeOwned + Serialize,
    M::Config: DeserializeOwned + Serialize,
{ /* private fields */ }

IQN agent implemented with tch-rs.

The type parameter M is a feature extractor, which takes M::Input and returns feature vectors.

Trait Implementations

impl<E, F, M, R> Agent<E, R> for Iqn<E, F, M, R>

where E: Env + 'static, F: SubModel<Output = Tensor> + 'static, M: SubModel<Input = Tensor, Output = Tensor> + 'static, R: ReplayBufferBase + 'static, E::Obs: Into<F::Input>, E::Act: From<Tensor>, F::Config: DeserializeOwned + Serialize + Clone, M::Config: DeserializeOwned + Serialize + Clone + OutDim, R::Batch: TransitionBatch, <R::Batch as TransitionBatch>::ObsBatch: Into<F::Input>, <R::Batch as TransitionBatch>::ActBatch: Into<Tensor>,

fn train(&mut self)

Switches the agent to training mode.

fn eval(&mut self)

Switches the agent to evaluation mode.

fn is_train(&self) -> bool

Returns whether the agent is currently in training mode.

fn opt_with_record(&mut self, buffer: &mut R) -> Record

Performs an optimization step and returns training metrics.

fn save_params(&self, path: &Path) -> Result<Vec<PathBuf>>

Saves the agent’s parameters to the specified directory.

fn load_params(&mut self, path: &Path) -> Result<()>

Loads the agent’s parameters from the specified directory.

fn as_any_mut(&mut self) -> &mut dyn Any

Returns a mutable reference to the agent as a type-erased Any value.

fn as_any_ref(&self) -> &dyn Any

Returns a reference to the agent as a type-erased Any value.

fn opt(&mut self, buffer: &mut R)

Performs a single optimization step using experiences from the replay buffer.

impl<E, F, M, R> Configurable for Iqn<E, F, M, R>

where E: Env, F: SubModel<Output = Tensor>, M: SubModel<Input = Tensor, Output = Tensor>, E::Obs: Into<F::Input>, E::Act: From<Tensor>, F::Config: DeserializeOwned + Serialize + Clone, M::Config: DeserializeOwned + Serialize + Clone + OutDim,

fn build(config: Self::Config) -> Self

Constructs Iqn agent.

type Config = IqnConfig<F, M>

The configuration type for this object.

fn build_from_path(path: impl AsRef<Path>) -> Result<Self, Error>

where Self: Sized,

Builds a new instance from a YAML configuration file.

impl<E, F, M, R> Policy<E> for Iqn<E, F, M, R>

where E: Env, F: SubModel<Output = Tensor>, M: SubModel<Input = Tensor, Output = Tensor>, E::Obs: Into<F::Input>, E::Act: From<Tensor>, F::Config: DeserializeOwned + Serialize + Clone, M::Config: DeserializeOwned + Serialize + Clone + OutDim,

fn sample(&mut self, obs: &E::Obs) -> E::Act

Samples an action given an observation from the environment.