Evolutionary synthesis of multi-agent systems for dynamic dial-a-ride problems

Lon, Rinde R.S. van; Holvoet, Tom; Berghe, Greet Vanden; Wenseleers, Tom; Branke, Juergen

doi:10.1145/2330784.2330832

Cited by 18 publications

(19 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…According to the search space, they are typically classified as heuristic selection (methodologies for choosing or selecting existing heuristics) and heuristic generation (methodologies for generating new heuristics from the components of existing ones). An even newer recent research trend is to employ human‐designed heuristics as building blocks to automatically generate new heuristics referred to a given problem or class of problems (Burke et al., ; van Lon et al., ).…”

Section: Related Workmentioning

confidence: 99%

Ejection chain moves for automatic neighborhood synthesis in constrained cardinality‐minimization problems

Adamo

Ghiani

Guerriero

et al. 2019

Int Trans Operational Res

View full text Add to dashboard Cite

In this paper, we deal with the problem of automatically synthesizing “good” neighborhoods for a specific class of problems, namely constrained cardinality‐minimization problems. Exploiting the peculiarity of the objective function of such problems, we develop automatic ejection chain moves that define neighborhood structures to be explored with a black‐box solver. In particular, starting from a formulation of a cardinality‐minimization problem and a feasible solution, our procedure automatically detects the “entities” involved in the problem and learns the strength of the relationships among them. This information is then used to define the characteristics of our moves that consist in ejecting one entity at a time from the solution. If one of such moves results in an infeasible solution, then feasibility is recovered by performing an additional step based on the solution of an auxiliary problem. The computational results show that, when assessed on four well‐known constrained cardinality‐minimization problems, our approach outperforms both a black‐box mixed integer programming solver and a state‐of‐the‐art model‐based neighborhood search procedure with respect to both solution quality and computing times.

show abstract

Section: Related Workmentioning

confidence: 99%

Ejection chain moves for automatic neighborhood synthesis in constrained cardinality‐minimization problems

Adamo

Ghiani

Guerriero

et al. 2019

Int Trans Operational Res

View full text Add to dashboard Cite

show abstract

“…Similarly, van Lon et al [14] used GP to evolve the guiding heuristic for a MAS in a dynamic PDPTW context. Vehicles have a capacity of one order, implying that a vehicle must immediately go to an order's destination after pick up.…”

Section: Distinguishes Two Different Categoriesmentioning

confidence: 99%

“…The work by Vonolfen et al [15] extends [14]. Instead of using just three variables in GP as was done in [14], Vonolfen et al use 18 different variables.…”

Section: Distinguishes Two Different Categoriesmentioning

confidence: 99%

“…Instead of using just three variables in GP as was done in [14], Vonolfen et al use 18 different variables. This includes several variables that include information about other agent's distances and destinations.…”

Section: Distinguishes Two Different Categoriesmentioning

confidence: 99%

“…The authors use the same MAS approach as in [14] but they evaluate their performance on an existing dynamic PDPTW benchmark. They are the first to report negative results, the reference centralized algorithm always outperforms the NEAT approach.…”

Section: Distinguishes Two Different Categoriesmentioning

confidence: 99%

See 2 more Smart Citations

Optimizing agents with genetic programming: an evaluation of hyper-heuristics in dynamic real-time logistics

Lon

Branke

Holvoet

2017

Genet Program Evolvable Mach

Self Cite

View full text Add to dashboard Cite

warwick.ac.uk/lib-publicationsOriginal citation: van Lon, Rinde R. S., Branke, Jürgen and Holvoet, Tom. (2017) Optimizing agents with genetic programming : an evaluation of hyper-heuristics in dynamic real-time logistics. Genetic Programming and Evolvable Machines. Permanent WRAP URL:http://wrap.warwick.ac.uk/86320 Copyright and reuse:The Warwick Research Archive Portal (WRAP) makes this work by researchers of the University of Warwick available open access under the following conditions. Copyright © and all moral rights to the version of the paper presented here belong to the individual author(s) and/or other copyright owners. To the extent reasonable and practicable the material made available in WRAP has been checked for eligibility before being made available.Copies of full items can be used for personal research or study, educational, or not-for profit purposes without prior permission or charge. Provided that the authors, title and full bibliographic details are credited, a hyperlink and/or URL is given for the original metadata page and the content is not changed in any way. Publisher's statement:The final publication is available at Springer via https://doi.org/10.1007/s10710-017-9300-5 A note on versions:The version presented here may differ from the published version or, version of record, if you wish to cite this item you are advised to consult the publisher's version. Please see the 'permanent WRAP url' above for details on accessing the published version and note that access may require a subscription. Abstract Dynamic pickup and delivery problems (PDPs) require online algorithms for managing a fleet of vehicles. Generally, vehicles can be managed either centrally or decentrally. A common way to coordinate agents decentrally is to use the contract-net protocol (CNET) that uses auctions to allocate tasks among agents. To participate in an auction, agents require a method that estimates the value of a task. Typically this method is an optimization algorithm. Recently, hyper-heuristics has been proposed for automated design of heuristics. Two properties of automatically designed heuristics are particularly promising: 1) a generated heuristic computes quickly, it is expected therefore that hyper-heuristics heuristics perform especially well for urgent problems, and 2) by using simulationbased evaluation, hyper-heuristics can learn from the past and can therefore create a 'rule of thumb' that anticipates situations in the future. In the present paper we empirically evaluate whether hyper-heuristics, more specifically genetic programming (GP), can be used to improve agents decentrally coordinated via CNET. We compare several GP settings and compare the resulting heuristic with existing centralized and decentralized algorithms on a dynamic PDP dataset with varying levels of dynamism, urgency, and scale. The results indicate that the evolved heuristic always outperforms the optimization algorithm in the decentralized MAS and often outperforms the centralized optimization algorithm. Our paper shows that des...

show abstract

A RNN-Based Hyper-heuristic for Combinatorial Problems

Kieffer

Duflo

Danoy

et al. 2022

Evolutionary Computation in Combinatorial Optimization

View full text Add to dashboard Cite

Designing efficient heuristics is a laborious and tedious task that generally requires a full understanding and knowledge of a given optimization problem. Hyper-heuristics have been mainly introduced to tackle this issue and are mostly relying on Genetic Programming and its variants. Many attempts in the literature have shown that an automatic training mechanism for heuristic learning is possible and can challenge human-based heuristics in terms of gap to optimality. In this work, we introduce a novel approach based on a recent work on Deep Symbolic Regression. We demonstrate that scoring functions can be trained using Recurrent Neural Networks to tackle a well-know combinatorial problem, i.e., the Multi-dimensional Knapsack. Experiments have been conducted on instances from the OR-Library and results show that the proposed modus operandi is an alternative and promising approach to humanbased heuristics and classical heuristic generation approaches.

show abstract

Evolutionary synthesis of multi-agent systems for dynamic dial-a-ride problems

Cited by 18 publications

References 14 publications

Ejection chain moves for automatic neighborhood synthesis in constrained cardinality‐minimization problems

Ejection chain moves for automatic neighborhood synthesis in constrained cardinality‐minimization problems

Optimizing agents with genetic programming: an evaluation of hyper-heuristics in dynamic real-time logistics

A RNN-Based Hyper-heuristic for Combinatorial Problems

Contact Info

Product

Resources

About