TabularQLearningAgent<T>
Models & Types · AiDotNet.ReinforcementLearning.Agents.TabularQLearning
Tabular Q-Learning agent using lookup table for Q-values.
Inheritance: ReinforcementLearningAgentBase<T> → TabularQLearningAgent<T>
Implements: IGradientComputable<T, Vector<T>, Vector<T>>
For Beginners
Q-Learning is like creating a cheat sheet: for every situation (state) and action you could take, you write down how good that choice is (Q-value). Over time, you update this sheet based on actual rewards you receive.
Key features:
- Off-Policy: Learns optimal policy while following exploratory policy
- Tabular: Uses lookup table, no function approximation
- Model-Free: Doesn’t need to know environment dynamics
- Value-Based: Learns action values, derives policy from them
Perfect for: Small discrete state/action spaces (grid worlds, simple games) Famous for: Watkins 1989, the foundation of modern RL
How It Works
Tabular Q-Learning is the foundational RL algorithm that maintains a table of Q-values for each state-action pair. No neural networks required.
Example
// Create a tabular Q-Learning agent for discrete state-action spaces
var options = new TabularQLearningOptions<double> { LearningRate = 0.1, StateSize = 4, ActionSize = 2 };
var agent = new TabularQLearningAgent<double>(options);
// Select an action using epsilon-greedy exploration
var state = new Vector<double>(new double[] { 0.5, -0.3, 1.0, 0.2 });
var action = agent.SelectAction(state);
Constructors
| Constructor | Summary |
|---|---|
TabularQLearningAgent() |
Initializes a new instance with default settings. |
TabularQLearningAgent(TabularQLearningOptions<T> options) |
Properties
| Property | Summary |
|---|---|
int FeatureCount { get; } |
Methods
| Method | Summary |
|---|---|
ModelMetadata<T> GetModelMetadata() |
|
T Train() |
|
Vector<T> ComputeGradients(Vector<T> input, Vector<T> target, ILossFunction<T> lossFunction) |
|
Vector<T> SelectAction(Vector<T> state, bool training) |
|
byte[] Serialize() |
Auto-generated common model serialization surface. |
void ApplyGradients(Vector<T> gradients, T learningRate) |
|
void Deserialize(byte[] data) |
Auto-generated common model deserialization surface. |
void LoadModel(string filepath) |
|
void SaveModel(string filepath) |
|
void StoreExperience(Vector<T> state, Vector<T> action, T reward, Vector<T> nextState, bool done) |