PolicyIterationAgent<T>

Models & Types ยท AiDotNet.ReinforcementLearning.Agents.DynamicProgramming

Policy Iteration agent for reinforcement learning using dynamic programming.

Inheritance: ReinforcementLearningAgentBase<T> โ†’ PolicyIterationAgent<T>

For Beginners

Policy Iteration works in two repeating steps:

  1. Evaluate: calculate how good the current strategy is for every state
  2. Improve: update the strategy to be greedy with respect to the evaluation These steps repeat until the strategy stops changing (convergence). It requires a complete model of the environment (transition probabilities and rewards) and works best for small, fully-known environments like grid worlds or simple games.

How It Works

Policy Iteration alternates between policy evaluation and policy improvement until convergence to the optimal policy.

Example

// Create a Policy Iteration agent for environments with known dynamics
var options = new PolicyIterationOptions<double> { StateSize = 4, ActionSize = 2 };
var agent = new PolicyIterationAgent<double>(options);
            
// Select an action using the current policy
var state = new Vector<double>(new double[] { 0.5, -0.3, 1.0, 0.2 });
var action = agent.SelectAction(state);

Constructors

Constructor Summary
PolicyIterationAgent() Initializes a new instance with default settings.
PolicyIterationAgent(PolicyIterationOptions<T> options)

Properties

Property Summary
int FeatureCount { get; }

Methods

Method Summary
Dictionary<string, T> GetMetrics()
ModelMetadata<T> GetModelMetadata()
T Train()
Task TrainAsync()
Task<Vector<T>> PredictAsync(Vector<T> input)
Vector<T> Predict(Vector<T> input)
Vector<T> SelectAction(Vector<T> state, bool training)
byte[] Serialize() Auto-generated common model serialization surface.
void Deserialize(byte[] data) Auto-generated common model deserialization surface.
void LoadModel(string filepath)
void ResetEpisode()
void SaveModel(string filepath)
void StoreExperience(Vector<T> state, Vector<T> action, T reward, Vector<T> nextState, bool done)