Results 1 - 10
of
14
Divide-and-Evolve: a New Memetic Scheme for DomainIndependent Temporal Planning
- LNCS, n o 3906
, 2006
"... Abstract. An original approach, termed Divide-and-Evolve is proposed to hybridize Evolutionary Algorithms (EAs) with Operational Research (OR) methods in the domain of Temporal Planning Problems (TPPs). Whereas standard Memetic Algorithms use local search methods to improve the evolutionary solution ..."
Abstract
-
Cited by 25 (18 self)
- Add to MetaCart
(Show Context)
Abstract. An original approach, termed Divide-and-Evolve is proposed to hybridize Evolutionary Algorithms (EAs) with Operational Research (OR) methods in the domain of Temporal Planning Problems (TPPs). Whereas standard Memetic Algorithms use local search methods to improve the evolutionary solutions, and thus fail when the local method stops working on the complete problem, the Divide-and-Evolve approach splits the problem at hand into several, hopefully easier, sub-problems, and can thus solve globally problems that are intractable when directly fed into deterministic OR algorithms. But the most prominent advantage of the Divide-and-Evolve approach is that it immediately opens up an avenue for multi-objective optimization, even though the OR method that is used is single-objective. Proof of concept approach on the standard (single-objective) Zeno transportation benchmark is given, and a small original multi-objective benchmark is proposed in the same Zeno framework to assess the multi-objective capabilities of the proposed methodology, a breakthrough in Temporal Planning. 1
Divide-and-Evolve: a Sequential Hybridization Strategy using Evolutionary Algorithms
"... Summary. An original approach, termed Divide-and-Evolve is proposed to hybridize Evolutionary Algorithms (EAs) with Operational Research (OR) methods in the domain of Temporal Planning Problems (TPPs). Whereas standard Memetic Algorithms use local search methods to improve the evolutionary solutions ..."
Abstract
-
Cited by 12 (7 self)
- Add to MetaCart
(Show Context)
Summary. An original approach, termed Divide-and-Evolve is proposed to hybridize Evolutionary Algorithms (EAs) with Operational Research (OR) methods in the domain of Temporal Planning Problems (TPPs). Whereas standard Memetic Algorithms use local search methods to improve the evolutionary solutions, and thus fail when the local method stops working on the complete problem, the Divideand-Evolve approach splits the problem at hand into several, hopefully easier, subproblems, and can thus solve globally problems that are intractable when directly fed into deterministic OR algorithms. But the most prominent advantage of the Divide-and-Evolve approach is that it immediately opens up an avenue for multiobjective optimization, even though the OR method that is used is single-objective. Proof of concept approach on the standard (single-objective) Zeno transportation benchmark is given, and a small original multi-objective benchmark is proposed in the same Zeno framework to assess the multi-objective capabilities of the proposed methodology, a breakthrough in Temporal Planning.
Automated creation of pattern database search heuristics
- In Proc. MoChArt-2006
"... Abstract. Pattern databases are dictionaries for heuristic estimates storing state-to-goal distances in state space abstractions. Their effectiveness is sensitive to the selection of the underlying patterns. Especially for multiple and additive pattern databases, the manual selection of patterns tha ..."
Abstract
-
Cited by 8 (1 self)
- Add to MetaCart
(Show Context)
Abstract. Pattern databases are dictionaries for heuristic estimates storing state-to-goal distances in state space abstractions. Their effectiveness is sensitive to the selection of the underlying patterns. Especially for multiple and additive pattern databases, the manual selection of patterns that leads to good exploration results is involved. For automating the selection process, greedy bin-packing has been suggested. This paper proposes genetic algorithms to optimize its output. Patterns are encoded as binary strings and optimized using an objective function that predicts the heuristic search tree size based on the distribution of heuristic values in abstract space. To reduce the memory requirements we construct the pattern databases symbolically. Experiments in heuristic search planning indicate that the total search efforts can be reduced significantly. 1
On the generality of parameter tuning in evolutionary planning
- Genetic and Evolutionary Computation Conference (GECCO
, 2010
"... Divide-and-Evolve (DaE) is an original “memeticization ” of Evolutionary Computation and Artificial Intelligence Planning. However, like any Evolutionary Algorithm, DaE has several parameters that need to be tuned, and the already excellent experimental results demonstrated by DaE on benchmarks from ..."
Abstract
-
Cited by 6 (5 self)
- Add to MetaCart
(Show Context)
Divide-and-Evolve (DaE) is an original “memeticization ” of Evolutionary Computation and Artificial Intelligence Planning. However, like any Evolutionary Algorithm, DaE has several parameters that need to be tuned, and the already excellent experimental results demonstrated by DaE on benchmarks from the International Planning Competition, at the level of those of standard AI planners, have been obtained with parameters that had been tuned once and for-all using the Racing method. This paper demonstrates that more specific parameter tuning (e.g. at the domain level or even at the instance level) can further improve DaE results, and discusses the trade-off between the gain in quality of the resulting plans and the overhead in terms of computational cost.
Instance-Based Parameter Tuning for Evolutionary AI Planning ABSTRACT
"... Learn-and-Optimize (LaO) is a generic surrogate based method for parameter tuning combining learning and optimization. In this paper LaO is used to tune Divide-and-Evolve (DaE), an Evolutionary Algorithm for AI Planning. The LaO framework makes it possible to learn the relation between some features ..."
Abstract
-
Cited by 2 (1 self)
- Add to MetaCart
(Show Context)
Learn-and-Optimize (LaO) is a generic surrogate based method for parameter tuning combining learning and optimization. In this paper LaO is used to tune Divide-and-Evolve (DaE), an Evolutionary Algorithm for AI Planning. The LaO framework makes it possible to learn the relation between some features describing a given instance and the optimal parameters for this instance, thus it enables to extrapolate this knowledge to unknown instances in the same domain. Moreover, the learned relation is used as a surrogate-model to accelerate the search for the optimal parameters. It hence becomes possible to solve intra-domain and extra-domain generalization in a single framework. The proposed implementation of LaO uses an Artificial Neural Network for learning the mapping between features and optimal parameters, and the Covariance Matrix Adaptation Evolution Strategy for optimization. Results demonstrate that LaO is capable of improving the quality of the DaE results even with only a few iterations. The main limitation of the DaE case-study is the limited amount of meaningful features that are available to describe the instances. However, the learned model reaches almost the same performance on the test instances, which means that it is capable of generalization.
Learn-and-Optimize: a Parameter Tuning Framework for Evolutionary AI Planning
"... Abstract. Learn-and-Optimize (LaO) is a generic surrogate based method for parameter tuning combining learning and optimization. In this paper LaO is used to tune Divide-and-Evolve (DaE), an Evolutionary Algorithm for AI Planning. The LaO framework makes it possible to learn the relation between som ..."
Abstract
-
Cited by 1 (0 self)
- Add to MetaCart
(Show Context)
Abstract. Learn-and-Optimize (LaO) is a generic surrogate based method for parameter tuning combining learning and optimization. In this paper LaO is used to tune Divide-and-Evolve (DaE), an Evolutionary Algorithm for AI Planning. The LaO framework makes it possible to learn the relation between some features describing a given instance and the optimal parameters for this instance, thus it enables to extrapolate this relation to unknown instances in the same domain. Moreover, the learned knowledge is used as a surrogate-model to accelerate the search for the optimal parameters. The proposed implementation of LaO uses an Artificial Neural Network for learning the mapping between features and optimal parameters, and the Covariance Matrix Adaptation Evolution Strategy for optimization. Results demonstrate that LaO is capable of improving the quality of the DaE results even with only a few iterations. The main limitation of the DaE case-study is the limited amount of meaningful features that are available to describe the instances. However, the learned model reaches almost the same performance on the test instances, which means that it is capable of generalization. 1
Sangjin Jung Gyu-Byung Park A Decomposition Method for Exploiting Parallel Computing Including the Determination of an Optimal Number of Subsystems
"... Many practical design problems are multidisciplinary and typically involve the transfer of complex information between analysis modules. In solving such problems, the method for performing multidisciplinary analyses greatly affects the speed of the total design time. Thus, it is very important to g ..."
Abstract
- Add to MetaCart
Many practical design problems are multidisciplinary and typically involve the transfer of complex information between analysis modules. In solving such problems, the method for performing multidisciplinary analyses greatly affects the speed of the total design time. Thus, it is very important to group and order a multidisciplinary analysis (MDA) process so as to minimize the total computational time and cost by decomposing a large multidisciplinary problem into several subsystems and then processing them in parallel. This study proposes a decomposition method that exploits parallel computing, including the determination of an optimal number of subsystems by using a multi-objective optimization formulation and a messy genetic algorithm (GA) modified to handle discrete design variables. In the suggested method, an MDA process is decomposed and sequenced for simultaneously minimizing the feedback couplings within each subsystem, the total couplings between subsystems, the variation of computation times among subsystems, and the computation time of each subsystem. The proposed method is applied to the decomposition of an artificial complex system example and a multidisciplinary design problem of a rotorcraft with 17 analysis modules; promising results are presented using this proposed method.
Automated Pattern Database Design
"... Pattern databases are dictionaries for heuristic estimates based on state-to-goal distances in state space abstractions. Their effectiveness is sensitive to the selection of the underlying patterns. Especially for multiple and additive pattern databases, a manual selection of pattern sets that lead ..."
Abstract
- Add to MetaCart
(Show Context)
Pattern databases are dictionaries for heuristic estimates based on state-to-goal distances in state space abstractions. Their effectiveness is sensitive to the selection of the underlying patterns. Especially for multiple and additive pattern databases, a manual selection of pattern sets that lead to good exploration results is involved. For automating the selection process, greedy bin-packing strategies have been suggested. This paper proposes genetic algorithms to optimize their output. Patterns are encoded as Boolean matrices and optimized using an objective function based on predicting the heuristic search tree size, given the distribution of heuristic values in the abstract state spaces. To reduce the memory requirements of the databases we apply a construction process based on BDDs. Experiments in heuristic search planning show that the search efforts are significantly reduced.
Proceedings of the Twentieth International Conference on Automated Planning and Scheduling (ICAPS 2010) An Evolutionary Metaheuristic Based on State Decomposition for Domain-Independent Satisficing Planning
"... DAEX is a metaheuristic designed to improve the plan quality and the scalability of an encapsulated planning system. DAEX is based on a state decomposition strategy, driven by an evolutionary algorithm, which benefits from the use of a classical planning heuristic to maintain an ordering of atoms wi ..."
Abstract
- Add to MetaCart
(Show Context)
DAEX is a metaheuristic designed to improve the plan quality and the scalability of an encapsulated planning system. DAEX is based on a state decomposition strategy, driven by an evolutionary algorithm, which benefits from the use of a classical planning heuristic to maintain an ordering of atoms within the individuals. The proof of concept is achieved by embedding the domain-independent satisficing YAHSP planner and using the critical path h 1 heuristic. Experiments with the resulting algorithm are performed on a selection of IPC benchmarks from classical, cost-based and temporal domains. Under the experimental conditions of the IPC, and in particular with a universal parameter setting common to all domains, DAEYAHSP is compared to the best planner for each type of domain. Results show that DAEYAHSP performs very well both on coverage and quality metrics. It is particularly noticeable that DAEX improves a lot on plan quality when compared to YAHSP, which is known to provide largely suboptimal solutions, making it competitive with state-of-the-art planners. This article gives a full account of the algorithm, reports on the experiments and provides some insights on the algorithm behavior.
Multi-Objective AI Planning: Comparing Aggregation and Pareto Approaches
, 2013
"... Abstract. Most real-world Planning problems are multi-objective, trying to minimize both the makespan of the solution plan, and some cost of the actions involved in the plan. But most, if not all existing approaches are based on single-objective planners, and use an aggregation of the objectives to ..."
Abstract
- Add to MetaCart
(Show Context)
Abstract. Most real-world Planning problems are multi-objective, trying to minimize both the makespan of the solution plan, and some cost of the actions involved in the plan. But most, if not all existing approaches are based on single-objective planners, and use an aggregation of the objectives to remain in the single-objective context. Divide-and-Evolve is an evolutionary planner that won the temporal deterministic satisficing track at the last International Planning Competitions (IPC). Like all Evolutionary Algorithms (EA), it can easily be turned into a Pareto-based Multi-Objective EA. It is however important to validate the resulting algorithm by comparing it with the aggregation approach: this is the goal of this paper. The comparative experiments on a recently proposed benchmark set that are reported here demonstrate the usefulness of going Pareto-based in AI Planning. 1
