PolicyIterationOptions<T>

Options & Configuration · AiDotNet.Models.Options

Configuration options for Policy Iteration agents.

Inheritance: ModelOptions → ReinforcementLearningOptions<T> → PolicyIterationOptions<T>

Constructors

Constructor Summary
PolicyIterationOptions()

Properties

Property Summary
double Theta { get; set; } Convergence threshold: policy evaluation stops once the largest value change in a sweep falls below it.
int ActionSize { get; set; } Number of discrete actions, or the dimension of the action vector for a continuous action space.
int MaxEvaluationIterations { get; set; } Maximum number of sweeps of each policy evaluation.
int StateSize { get; set; } Number of features in one observation of the environment state.