DoubleDQNOptions<T>
Options & Configuration ยท AiDotNet.Models.Options
Configuration options for Double DQN agent.
Inheritance: ModelOptions โ DoubleDQNOptions<T>
Constructors
| Constructor | Summary |
|---|---|
DoubleDQNOptions() |
Creates options with the default values. |
Properties
| Property | Summary |
|---|---|
ILossFunction<T> LossFunction { get; set; } |
Loss function for training. |
List<int> HiddenLayers { get; set; } |
Hidden layer sizes for the Q-network. |
T DiscountFactor { get; set; } |
Discount factor (gamma) for future rewards. |
T LearningRate { get; set; } |
Learning rate for gradient updates. |
double EpsilonDecay { get; set; } |
Multiplicative decay factor applied to epsilon each episode. |
double EpsilonEnd { get; set; } |
Final exploration rate. |
double EpsilonStart { get; set; } |
Initial exploration rate for epsilon-greedy policy. |
int ActionSize { get; set; } |
Number of discrete actions available to the agent. |
int BatchSize { get; set; } |
Number of experiences sampled per training update. |
int ReplayBufferSize { get; set; } |
Maximum number of experiences stored in the replay buffer. |
int StateSize { get; set; } |
Dimension of the environment state vector. |
int TargetUpdateFrequency { get; set; } |
Number of steps between target network updates. |
int WarmupSteps { get; set; } |
Number of random steps before training begins. |