Free cookie consent management tool by TermsFeed Policy Generator

source: branches/3.1/sources/HeuristicLab.ES/SelfAdaptiveMutationStrengthAdjuster.cs @ 11315

Last change on this file since 11315 was 99, checked in by abeham, 17 years ago

Added sigma self adaptive operators for RealVector problems

File size: 2.7 KB
Line 
1#region License Information
2/* HeuristicLab
3 * Copyright (C) 2002-2008 Heuristic and Evolutionary Algorithms Laboratory (HEAL)
4 *
5 * This file is part of HeuristicLab.
6 *
7 * HeuristicLab is free software: you can redistribute it and/or modify
8 * it under the terms of the GNU General Public License as published by
9 * the Free Software Foundation, either version 3 of the License, or
10 * (at your option) any later version.
11 *
12 * HeuristicLab is distributed in the hope that it will be useful,
13 * but WITHOUT ANY WARRANTY; without even the implied warranty of
14 * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
15 * GNU General Public License for more details.
16 *
17 * You should have received a copy of the GNU General Public License
18 * along with HeuristicLab. If not, see <http://www.gnu.org/licenses/>.
19 */
20#endregion
21
22using System;
23using System.Collections.Generic;
24using System.Text;
25using HeuristicLab.Core;
26using HeuristicLab.Data;
27using HeuristicLab.Random;
28
29namespace HeuristicLab.ES {
30  public class SelfAdaptiveMutationStrengthAdjuster : OperatorBase {
31    public override string Description {
32      get { return @"Mutates the endogenous strategy parameters"; }
33    }
34
35    public SelfAdaptiveMutationStrengthAdjuster()
36      : base() {
37      AddVariableInfo(new VariableInfo("Random", "Pseudo random number generator", typeof(IRandom), VariableKind.In));
38      AddVariableInfo(new VariableInfo("StrategyVector", "Vector containing the endogenous strategy parameters", typeof(DoubleArrayData), VariableKind.In));
39      AddVariableInfo(new VariableInfo("GeneralLearningRate", "The general learning rate will scale all mutations. It's influence is calculated as: e^(GeneralLearningRate*N(0,1))", typeof(DoubleData), VariableKind.In));
40      AddVariableInfo(new VariableInfo("LearningRate", "Learning parameter defines the strength of the adaption of each component in the object parameter vector", typeof(DoubleData), VariableKind.In));
41    }
42
43    public override IOperation Apply(IScope scope) {
44      IRandom random = GetVariableValue<IRandom>("Random", scope, true);
45      double[] strategyParams = GetVariableValue<DoubleArrayData>("StrategyVector", scope, false).Data;
46      double tau = GetVariableValue<DoubleData>("LearningRate", scope, true).Data;
47      double tau0 = GetVariableValue<DoubleData>("GeneralLearningRate", scope, true).Data;
48
49      NormalDistributedRandom N = new NormalDistributedRandom(random, 0.0, 1.0);
50      double generalMultiplier = Math.Exp(tau0 * N.NextDouble());
51      for (int i = 0; i < strategyParams.Length; i++) {
52        strategyParams[i] *= generalMultiplier * Math.Exp(tau * N.NextDouble());
53      }
54      return base.Apply(scope);
55    }
56  }
57}
Note: See TracBrowser for help on using the repository browser.