OffPolicyMonteCarloOptions<T>

Options & Configuration · AiDotNet.Models.Options

Configuration options for Off-Policy Monte Carlo Control agents with importance sampling.

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

Constructors

Constructor Summary
OffPolicyMonteCarloOptions()

Properties

Property Summary
double BehaviorEpsilon { get; set; } Exploration rate of the epsilon-greedy behavior policy that generates episodes; returns are reweighted by importance sampling toward the greedy target policy.
int ActionSize { get; set; } Number of discrete actions, or the dimension of the action vector for a continuous action space.
int StateSize { get; set; } Number of features in one observation of the environment state.