PrioritizedSweepingAgent<T>

Models & Types ยท AiDotNet.ReinforcementLearning.Agents.Planning

Prioritized Sweeping agent that focuses planning on high-priority state-actions.

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

For Beginners

Prioritized Sweeping is like Dyna-Q but smarter about which simulated updates to do. Instead of replaying random past experiences, it prioritizes updates where the biggest changes happened. Think of it like studying: focus on the topics where you got the most wrong. A priority queue tracks which state-actions need the most urgent updates, making planning much more efficient.

Example

// Create a Prioritized Sweeping agent for efficient planning
var options = new PrioritizedSweepingOptions<double> { PlanningSteps = 10, StateSize = 4, ActionSize = 2 };
var agent = new PrioritizedSweepingAgent<double>(options);
            
// Select an action and update priorities based on TD error
var state = new Vector<double>(new double[] { 0.5, -0.3, 1.0, 0.2 });
var action = agent.SelectAction(state);

Constructors

Constructor Summary
PrioritizedSweepingAgent() Initializes a new instance with default settings.
PrioritizedSweepingAgent(PrioritizedSweepingOptions<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)