Abstract
In this paper the strategy for the A-Team with Reinforcement Learning (RL) approach for solving the Multi-mode Resource-Constrained Project Scheduling Problem (MRCPSP) is proposed and experimentally validated. The MRCPSP belongs to the NP-hard problem class. To solve this problem a team of asynchronous agents (A-Team) has been implemented using multiagent system. An A-Team is the set of objects including multiple agents and the common memory which through interactions produce solutions of optimization problems. These interactions are usually managed by the static strategy. In this paper the dynamic learning strategy is suggested. The proposed strategy based on reinforcement learning supervises interactions between optimization agents and the common memory. To validate the proposed approach computational experiment has been carried out.
This is a preview of subscription content, log in via an institution.
Buying options
Tax calculation will be finalised at checkout
Purchases are for personal use only
Learn about institutional subscriptionsNotes
- 1.
See PSPLIB at http://www.om-db.wi.tum.de/psplib/.
References
Barbucha, D., Czarnowski, I., Jędrzejowicz, P., Ratajczak-Ropel, E., Wierzbowska, I.: Influence of the working strategy on A-team performance, smart information and knowledge management. In: Szczerbicki, E., Nguyen, N.T. (eds.) Studies in Computational Intelligence, vol. 260, pp. 83–102 (2010)
Barbucha, D.: Search modes for the cooperative multi-agent system solving the vehicle routing problem. Intell. Auton. Syst. Neurocomput. 88, 13–23 (2012)
Barto, A.G., Sutton, R.S., Anderson, C.W.: Neuronlike adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. SMC-13, 835–846 (1983)
Bellifemine, F., Caire, G., Poggi, A., Rimassa, G.: JADE. A White Paper Exp. 3(3), 6–20 (2003)
Błażewicz, J., Lenstra, J., Rinnooy, A.: Scheduling subject to resource constraints: Classification and complexity. Discrete Appl. Math. 5, 11–24 (1983)
Cadenas, J.M., Garrido, M.C., Muñoz, E.: Using machine learning in a cooperative hybrid parallel strategy of metaheuristics. Inf. Sci. 179(19), 3255–3267 (2009)
Lova, A., Tormos, P., Cervantes, M., Barber, F.: An efficient hybrid genetic algorithm for scheduling projects with resource constraints and multiple execution modes. Int. J. Prod. Econ. 117(2), 302–316 (2009)
Jędrzejowicz, P., Wierzbowska, I.: JADE-based A-team environment. Comput. Sci.–ICCS. Lect. Notes Comput. Sci. 3993, 719–726 (2006)
Jędrzejowicz, P., Ratajczak-Ropel, E.: New generation A-Team for solving the resource constrained project scheduling. In: Proceedings of the Eleventh International Workshop on Project Management and Scheduling, pp. 156–159. Istanbul (2008)
Jędrzejowicz, P., Ratajczak-Ropel, E.: Reinforcement learning strategies for A-team solving the resource-constrained project scheduling problem. Neurocomputing 146, 301–307 (2014)
Kolisch, R.: Project scheduling under resource constraints–Efficient heuristics for several problem classes. Ph.D. thesis, Physica, Heidelberg (1995)
Liu, S., Chen, D., Wang, Y.: Memetic algorithm for multi-mode resource-constrained project scheduling problems. J. Syst. Eng. Electron. 25(4), 609–617 (2014)
Nareyek, A.: Choosing Search Heuristics by Non-Stationary Reinforcement Learning Metaheuristics: Computer Decision-Making. Academic Publishers, Kluwer (2001)
Talukdar, S., BaerentzenL, G.A, De Souza, P.: Asynchronous teams: Co-operation schemes for autonomous, computer-based agents. In: Technical Report EDRC 18–59-96, Carnegie Mellon University, Pittsburgh (1996)
Van Peteghem, V., Vanhoucke, M.: A genetic algorithm for the preemptive and non-preemptive multi-mode resource-constrained project scheduling problems. Eur. J. Oper. Res. 201(2), 409–418 (2010)
Ranjbar, M., Reyck, B., De Kianfar, F.: A hybrid scatter search for the discrete time/resource trade-off problem in project scheduling. E. J. Oper. Res. 193(1), 35–48 (2009)
Wauters, T.: Reinforcement learning enhanced heuristic search for combinatorial optimization, Doctoral thesis, Department of Computer Science, KU Leuven (2012)
Węglarz, J., Józefowska, J., Mika, M., Waligora, G.: Project scheduling with finite or infinite number of activity processing modes–a survey. Eur. J. Oper. Res. 208, 177–205 (2011)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2015 Springer International Publishing Switzerland
About this paper
Cite this paper
Jędrzejowicz, P., Ratajczak-Ropel, E. (2015). Reinforcement Learning Strategy for Solving the MRCPSP by a Team of Agents. In: Neves-Silva, R., Jain, L., Howlett, R. (eds) Intelligent Decision Technologies. IDT 2017. Smart Innovation, Systems and Technologies, vol 39. Springer, Cham. https://doi.org/10.1007/978-3-319-19857-6_46
Download citation
DOI: https://doi.org/10.1007/978-3-319-19857-6_46
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-19856-9
Online ISBN: 978-3-319-19857-6
eBook Packages: EngineeringEngineering (R0)