HyperNetMetaRLOptions<T, TInput, TOutput>
Options & Configuration ยท AiDotNet.MetaLearning.Options
Configuration options for HyperNet Meta-RL: hypernetwork-based policy generation for meta-reinforcement learning.
Inheritance: ModelOptions โ HyperNetMetaRLOptions<T, TInput, TOutput>
Implements: IMetaLearnerOptions<T>
How It Works
HyperNet Meta-RL uses a hypernetwork to generate task-specific policy parameters from a task embedding. The task embedding is computed from initial task interaction data (support set), and the hypernetwork transforms it into a full parameter vector for the policy network, enabling single-forward-pass adaptation.
Constructors
| Constructor | Summary |
|---|---|
HyperNetMetaRLOptions(IFullModel<T, TInput, TOutput> metaModel) |
Creates options for meta-learning metaModel, with the default settings. |
Properties
| Property | Summary |
|---|---|
IEpisodicDataLoader<T, TInput, TOutput> DataLoader { get; set; } |
Episodic data loader that supplies the meta-training tasks; null when tasks are passed to training directly. |
IFullModel<T, TInput, TOutput> MetaModel { get; set; } |
The model whose parameters the meta-learner trains to adapt quickly to new tasks. |
IGradientBasedOptimizer<T, TInput, TOutput> InnerOptimizer { get; set; } |
Optimizer for task adaptation. |
IGradientBasedOptimizer<T, TInput, TOutput> MetaOptimizer { get; set; } |
Optimizer for the meta-update. |
ILossFunction<T> LossFunction { get; set; } |
Loss function for meta-training; null uses the default regression loss. |
bool EnableCheckpointing { get; set; } |
|
bool UseFirstOrder { get; set; } |
Whether to use the first-order approximation of the meta-gradient. |
double InnerLearningRate { get; set; } |
|
double OuterLearningRate { get; set; } |
|
double ParamRegWeight { get; set; } |
Weight for the parameter regularization loss. |
double? GradientClipThreshold { get; set; } |
|
int AdaptationSteps { get; set; } |
|
int CheckpointFrequency { get; set; } |
|
int EvaluationFrequency { get; set; } |
|
int EvaluationTasks { get; set; } |
|
int HyperNetHiddenDim { get; set; } |
Hidden dimension of the hypernetwork. |
int MetaBatchSize { get; set; } |
|
int NumMetaIterations { get; set; } |
|
int TaskEmbeddingDim { get; set; } |
Dimensionality of the task embedding. |
int? RandomSeed { get; set; } |
Methods
| Method | Summary |
|---|---|
IMetaLearnerOptions<T> Clone() |
|
bool IsValid() |