RLAutoMLOptions<T>
Options & Configuration · AiDotNet.Configuration
Configuration options for running AutoML over reinforcement learning agents and hyperparameters.
For Beginners
RL AutoML tries a few different RL agent settings, measures which one earns the most reward, and then trains the best configuration for your full training budget.
How It Works
This options class is designed for use with AiModelBuilder when training RL agents.
It supports the AiDotNet facade pattern by providing sensible defaults while allowing customization.
Constructors
| Constructor | Summary |
|---|---|
RLAutoMLOptions() |
Properties
| Property | Summary |
|---|---|
Dictionary<string, ParameterRange> SearchSpaceOverrides { get; set; } |
Gets or sets optional hyperparameter search-space overrides. |
List<RLAutoMLAgentType> CandidateAgents { get; set; } |
Gets or sets the allowed agent types for RL AutoML. |
int EvaluationEpisodesPerTrial { get; set; } |
Gets or sets the number of evaluation episodes to run per AutoML trial (no learning). |
int TrainingEpisodesPerTrial { get; set; } |
Gets or sets the number of training episodes to run per AutoML trial. |
int? MaxStepsPerEpisodeOverride { get; set; } |
Gets or sets an optional maximum step count per episode override for AutoML trials. |