IPolicy<T>
Interfaces · AiDotNet.ReinforcementLearning.Policies
Core interface for RL policies - defines how to select actions.
Implements: IDisposable
Known implementations: PolicyBase<T>
Methods
| Method | Summary |
|---|---|
IReadOnlyList<INeuralNetwork<T>> GetNetworks() |
Gets the neural networks used by this policy. |
T ComputeLogProb(Vector<T> state, Vector<T> action) |
Computes the log probability of a given action in a given state. |
Vector<T> SelectAction(Vector<T> state, bool training) |
Selects an action given the current state. |
void Reset() |
Resets any internal state (e.g., for recurrent policies, exploration noise). |