EpsilonGreedyExploration<T>

Models & Types ยท AiDotNet.ReinforcementLearning.Policies.Exploration

Epsilon-greedy exploration: with probability epsilon, select random action.

Inheritance: ExplorationStrategyBase<T> โ†’ EpsilonGreedyExploration<T>

Example

var random = new Random(42);
var state = new Vector<double>(new double[] { 0.1, -0.4, 0.7, 0.2 });
// Create epsilon-greedy exploration with annealing from 1.0 to 0.01
var exploration = new EpsilonGreedyExploration<double>(epsilonStart: 1.0, epsilonEnd: 0.01, epsilonDecay: 0.995);
            
// With probability epsilon, select a random action instead of the policy action
var policyAction = new Vector<double>(new double[] { 0.0, 1.0, 0.0 });
var action = exploration.GetExplorationAction(state, policyAction, actionSpaceSize: 3, random);

Constructors

Constructor Summary
EpsilonGreedyExploration(double epsilonStart, double epsilonEnd, double epsilonDecay)

Properties

Property Summary
double CurrentEpsilon { get; }

Methods

Method Summary
Vector<T> GetExplorationAction(Vector<T> state, Vector<T> policyAction, int actionSpaceSize, Random random)
void Reset()
void Update()