InContextRLOptions<T, TInput, TOutput>

Options & Configuration ยท AiDotNet.MetaLearning.Options

Configuration options for In-Context RL: meta-RL via in-context adaptation without explicit gradient updates at test time.

Inheritance: ModelOptions โ†’ InContextRLOptions<T, TInput, TOutput>

Implements: IMetaLearnerOptions<T>

How It Works

In-Context RL trains a model to perform RL adaptation purely through its forward pass, without any gradient updates at test time. The model conditions on a context buffer of past (input, output, loss) triplets and learns to improve its predictions based on this growing context. During meta-training, the context is built sequentially.

Constructors

Constructor Summary
InContextRLOptions(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; } Must stay null: this algorithm takes no plain gradient inner step (it adapts without one, or by its own update rule), so a supplied optimizer is rejected when the learner is built.
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 ContextPredictionWeight { get; set; } Weight for the context prediction loss (auxiliary).
double InnerLearningRate { get; set; }
double OuterLearningRate { get; set; }
double? GradientClipThreshold { get; set; }
int AdaptationSteps { get; set; }
int CheckpointFrequency { get; set; }
int ContextBufferSize { get; set; } Maximum size of the in-context buffer.
int ContextEmbeddingDim { get; set; } Dimensionality of context embeddings per entry.
int EvaluationFrequency { get; set; }
int EvaluationTasks { get; set; }
int MetaBatchSize { get; set; }
int NumMetaIterations { get; set; }
int? RandomSeed { get; set; }

Methods

Method Summary
IMetaLearnerOptions<T> Clone()
bool IsValid()