Abstract
Reinforcement learning techniques for solving complex problems are resource-intensive and take a long time to converge, prompting a need for methods that encourage faster learning. In this paper we show our successful application of actor-critic reinforcement learning to the air combat simulation domain and how reward structures affect the learning speed to find effective air combat tactics.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
References
Alford, R., Borck, H., Karneeb, J., Aha, D.: Active behavior recognition in beyond visual range air combat. In: Proceedings of the Third Annual Conference on Advances in Cognitive Systems (2015)
Barto, A., Sutton, R.S., Anderson, C.W.: Neuron-like adaptive elements that can solve difficult learning control problems. IEEE Trans. Syst. Man Cybern. 9, 833–836 (1983)
Bengio, Y., Louradour, J., Collobert, R., Weston, J.: Curriculumm learning. In: Proceedings of the 26th Annual International Conference on Machine Learning, pp. 41–48 (2009)
Fang, J., Yan, W.J., Fang, W.: Air combat strategies of CGF based on Q-learning and behavior tree. DEStech Trans. Eng. Technol. Res. (2017)
Floyd, M.W., Karneeb, J., Moore, P., Aha, D.W.: A goal reasoning agent for controlling UAVs in beyond-visual-range air combat. In: Proceedings 26th International Joint Conference on Artificial Intelligence (2017)
Grześ, M., Kudenko, D.: Improving optimistic exploration in model-free reinforcement learning. In: Kolehmainen, M., Toivanen, P., Beliczynski, B. (eds.) ICANNGA 2009. LNCS, vol. 5495, pp. 360–369. Springer, Heidelberg (2009). https://doi.org/10.1007/978-3-642-04921-7_37
Heinze, C., Papasimeon, M., Goss, S., Cross, M., Connell, R.: Simulating fighter pilots. In: Defence Industry Applications of Autonomous Agents and Multi-Agent Systems, pp. 113–130 (2007)
Lee, D., Bang, H.: Planar evasive aircrafts maneuvers using reinforcement learning. In: Lee, S., Cho, H., Yoon, K.J., Lee, J. (eds.) Intelligent Autonomous Systems. AISC, vol. 193, pp. 533–542. Springer, Heidelberg (2013). https://doi.org/10.1007/978-3-642-33926-4_49
Liu, P., Ma, Y.: A deep reinforcement learning based intelligent decision method for UCAV air combat. In: Mohamed Ali, M.S., Wahid, H., Mohd Subha, N.A., Sahlan, S., Md. Yunus, M.A., Wahap, A.R. (eds.) AsiaSim 2017. CCIS, vol. 751, pp. 274–286. Springer, Singapore (2017). https://doi.org/10.1007/978-981-10-6463-0_24
Masek, M., Lam, C.P., Benke, L., Kelly, L., Papasimeon, M.: Discovering emergent agent behaviour with evolutionary finite state machines. In: Miller, T., Oren, N., Sakurai, Y., Noda, I., Savarimuthu, B.T.R., Cao Son, T. (eds.) PRIMA 2018. LNCS, vol. 11224, pp. 19–34. Springer, Cham (2018). https://doi.org/10.1007/978-3-030-03098-8_2
McGrew, J., How, J.P., Williams, B., Roy, N.: Air-combat strategy using approximate dynamic programming. J. Guidance Control Dyn. 33, 1641–1654 (2010)
Mizokami, K.: This chart explains how crazy-expensive fighter jets Have Gotten. Popular Mechanics, March 2017
Mnih, V., et al.: Human-level control through deep reinforcement learning. Nature 518, 29–33 (2015)
Mnih, V., et al.: Asynchronous methods for deep reinforcement learning. In: Proceedings 33rd International Conference on Machine Learning, vol. 48, pp. 1928–1937 (2016)
Mouton, H., Roodt, J., le Roux, H.: Applying reinforcement learning to the weapon assignment problem in air defence. Scientia Militaria S. Afr. J. Mil. Stud. 123–140 (2011)
Park, H., Lee, B., Takh, M.: Differential game based air combat maneuver generation using scoring function matrix. Int. J. Aeronaut. Space Sci. 17(2), 204–213 (2016)
Ramirez, M., et al.: Integrated hybrid planning and programmed control for real time UAV maneuvering. In: Proceedings 17th International Conference on Autonomous Agents and MultiAgent Systems, pp. 1318–1326 (2018)
Rodin, E.Y., Amin, S.M.: Maneuver prediction in air combat via artificial neural networks. Comput. Math. Appl. 24(3), 95–112 (1982)
Roijers, D.M., Vamplew, P., Whiteson, S., Dazeley, R.: A survey of multi-objective sequential decision-making. J. Artif. Intell. Res. 48, 67–113 (2013)
Shalev, S., Shammah, S., Shashua, A.: Safe, multi-agent, reinforcement learning for autonomous driving: CoRR, vol abs/1610.03295 (2016)
Shaw, R.L.: Fighter Combat: Tactics and Maneuvering. Naval Institute Press, Annapolis (1985)
Sherstov, A.A., Stone, P.: Three automated stock-trading agents: a comparative study. In: Faratin, P., RodrÃguez-Aguilar, J.A. (eds.) AMEC 2004. LNCS (LNAI), vol. 3435, pp. 173–187. Springer, Heidelberg (2006). https://doi.org/10.1007/11575726_13
Silver, D., et al.: Mastering the game of Go with deep neural networks and tree search. Nature 529, 484 (2016)
Sutton, R., Barto, A.: Reinforcement Learning: An Introduction, 2nd edn. MIT Press, Cambridge (2018)
Sutton, R., McAllester, D., Singh, S., Mansour, Y.: Policy gradient methods for reinforcement learning with function approximation. In: Advances in Neural Information Processing Systems, pp. 1057–1063 (2000)
Teng, T.H., Tan, A.H., Tan, Y.S., Yeo, A.: Self-organizing neural networks for learning air combat maneuvers: In: IEEE World Congress on Computational Intelligence, Brisbane, Australia (2012)
Vamplew, P., Dazeley, R., Berry, A., Issabekov, R., Dekker, E.: Empirical evaluation methods for multiobjective reinforcement learning algorithms. Mach. Learn. 84, 51 (2011)
Vinberg, D.: Guided reinforcement learning applied to air-combat simulation. Master ’s thesis. Royal Institute of Technology, Sweden (2010)
Wharington, J.: Autonomous control of soaring aircraft by reinforcement learning. Doctorate thesis at Royal Melbourne Institute of Technology (1998)
Acknowledgements
This research is supported by the Defence Science and Technology Group, Australia; the Defence Science Institute, Australia; and an Australian Government Research Training Program Fee-offset scholarship. Associate Professor Joarder Kamruzzaman of the Centre for Multimedia Computing, Communications, and Artificial Intelligence Research (MCCAIR) at Federation University contributed some of the computing resources for this project.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2019 Springer Nature Switzerland AG
About this paper
Cite this paper
Kurniawan, B., Vamplew, P., Papasimeon, M., Dazeley, R., Foale, C. (2019). An Empirical Study of Reward Structures for Actor-Critic Reinforcement Learning in Air Combat Manoeuvring Simulation. In: Liu, J., Bailey, J. (eds) AI 2019: Advances in Artificial Intelligence. AI 2019. Lecture Notes in Computer Science(), vol 11919. Springer, Cham. https://doi.org/10.1007/978-3-030-35288-2_5
Download citation
DOI: https://doi.org/10.1007/978-3-030-35288-2_5
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-030-35287-5
Online ISBN: 978-3-030-35288-2
eBook Packages: Computer ScienceComputer Science (R0)