Self-Adaptivity for Constraint Satisfaction: Learning Penalty Functions
نویسندگان
چکیده
|Treating constrained problems with EAs is a big challange to the eld. Whether one considers constrained optmization problems or constraint satisfaction problems, the presence of a tness function (penalty function) reeect-ing consraint violation is essential. The deenition of such a penalty function has a great impact on the GA performance , and it is therefore very important to chose it properly. In this paper we show that ad hoc setting of penalties for constraint violations can be circumvented by using self-adaptivity. We illustrate the matter on a discrete CSP, the Zebra problem, and show that the penalties learned by the GA are to a big extent independent from the applied genetic operators as well as from the initial constraint weights.
منابع مشابه
Soft Constraints and Exact Penalty Functions in Model Predictive Control
One of the strengths of Model Predictive Control (MPC) is its ability to incorporate constraints in the control formulation. Often a disturbance drives the system into a region where the MPC problem is infeasible and hence no control action can be computed. Feasibility can be recovered by softening the constraints using slack variables. This approach does not necessarily guarantee that the cons...
متن کاملThe island confinement method for reducing search space in local search methods
Typically local search methods for solving constraint satisfaction problems such as GSAT, WalkSAT, DLM, and ESG treat the problem as an optimization problem. Each constraint contributes part of a penalty function in assessing trial valuations. Local search examines the neighbours of the current valuation, using the penalty function to determine a “better” neighbour valuation to move to, until f...
متن کاملیادگیری نیمه نظارتی کرنل مرکب با استفاده از تکنیکهای یادگیری معیار فاصله
Distance metric has a key role in many machine learning and computer vision algorithms so that choosing an appropriate distance metric has a direct effect on the performance of such algorithms. Recently, distance metric learning using labeled data or other available supervisory information has become a very active research area in machine learning applications. Studies in this area have shown t...
متن کاملSolving CSPs using self-adaptive constraint weights: how to prevent EAs from cheating
This paper examines evolutionary algorithms (EAs) extended by various penalty-based approaches to solve constraint satisfaction problems (CSPs). In some approaches, the penalties are set in advance and they do not change during a run. In other approaches, dynamic or adaptive penalties that change during a run according to some mechanism (a heuristic rule or a feedback), are used. In this work w...
متن کاملUsing Self-learning and Automatic Tuning to Improve the Performance of Sexual Genetic Algorithms for Constraint Satisfaction Problems
Currently the parameters in a constraint solver are often selected by hand by experts in the field; these parameters might include the level of preprocessing to be used and the variable ordering heuristic. The efficient and automatic choice of a preprocessing level for a constraint solver is a step towards making constraint programming a more widely accessible technology. Self-learning sexual g...
متن کامل