Abstract
Motivated by the goal recognition (GR) and goal recognition design (GRD) problems in the artificial intelligence (AI) planning domain, we introduce and study two natural variants of the GR and GRD problems with strategic agents, respectively. More specifically, we consider game-theoretic (GT) scenarios where a malicious adversary aims to damage some target in an (physical or virtual) environment monitored by a defender. The adversary must take a sequence of actions in order to attack the intended target. In the GTGR and GTGRD settings, the defender attempts to identify the adversary’s intended target while observing the adversary’s available actions so that he/she can strengthens the target’s defense against the attack. In addition, in the GTGRD setting, the defender can alter the environment (e.g., adding roadblocks) in order to better distinguish the goal/target of the adversary.
We propose to model GTGR and GTGRD settings as zero-sum stochastic games with incomplete information about the adversary’s intended target. The games are played on graphs where vertices represents states and edges are adversary’s actions. For the GTGR setting, we show that if the defender is restricted to playing only stationary strategies, the problem of computing optimal strategies (for both defender and adversary) can be formulated and represented compactly as a linear program. For the GTGRD setting, where the defender can choose K edges to block at the start of the game, we formulate the problem of computing optimal strategies as a mixed integer program, and present a heuristic algorithm based on LP duality and greedy methods. Experiments show that our heuristic algorithm achieves good performance (i.e., close to defender’s optimal value) with better scalability compared to the mixed-integer programming approach.
In contrast with our research, existing work, especially on GRD problems, has focused almost exclusively on decision-theoretic paradigms, where the adversary chooses its actions without taking into account the fact that they may be observed by the defender. As such an assumption is unrealistic in GT scenarios, our proposed models and algorithms fill a significant gap in the literature.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
Another perspective: from the previous section we see that \(\lambda ^\theta _{s,j}\) is the probability that adversary type \(\theta \) traverses the edge s, j. Then if the adversary and defender do not change their strategies after the edge (s, j) is blocked, the defender would receive an additional utility of \(M\sum _{\theta \in B} \lambda ^\theta _{s,j}\) from the adversary’s penalty for crossing that edge.
References
Braynov, S.: Adversarial planning and plan recognition: two sides of the same coin. In: Proceedings of the Secure Knowledge Management Workshop (2006)
Fudenberg, D., Tirole, J.: Game Theory. The MIT Press, Cambridge (1991)
Geib, C., Steedman, M.: On natural language processing and plan recognition. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 1612–1617 (2007)
Guillarme, N.L., Mouaddib, A.I., Lerouvreur, X., Gatepaille, S.: A generative game-theoretic framework for adversarial plan recognition. In: Proceedings of the Workshop on Distributed and Multi-Agent Planning (2015)
Jarvis, P., Lunt, T., Myers, K.: Identifying terrorist activity with AI plan recognition technology. AI Mag. 26(3), 73–81 (2005)
Johnson, W.L.: Serious use of a serious game for language learning. Int. J. Artif. Intell. Educ. 20(2), 175–195 (2010)
Kautz, H.A.: A formal theory of plan recognition. Ph.D. thesis, Bell Laboratories (1987)
Kelley, R., Wigand, L., Hamilton, B., Browne, K., Nicolescu, M., Nicolescu, M.: Deep networks for predicting human intent with respect to objects. In: Proceedings of the International Conference on Human-Robot Interaction (HRI), pp. 171–172 (2012)
Keren, S., Gal, A., Karpas, E.: Goal recognition design. In: Proceedings of the International Conference on Automated Planning and Scheduling (ICAPS), pp. 154–162 (2014)
Keren, S., Gal, A., Karpas, E.: Goal recognition design for non-optimal agents. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 3298–3304 (2015)
Keren, S., Gal, A., Karpas, E.: Goal recognition design with non-observable actions. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 3152–3158 (2016)
Lee, S.Y., Mott, B.W., Lester, J.C.: Real-time narrative-centered tutorial planning for story-based learning. In: Cerri, S.A., Clancey, W.J., Papadourakis, G., Panourgia, K. (eds.) ITS 2012. LNCS, vol. 7315, pp. 476–481. Springer, Heidelberg (2012). doi:10.1007/978-3-642-30950-2_61
Lisý, V., Píbil, R., Stiborek, J., Bosanský, B., Pechoucek, M.: Game-theoretic approach to adversarial plan recognition. In: Proceedings of the European Conference on Artificial Intelligence (ECAI), pp. 546–551 (2012)
McQuiggan, S.W., Rowe, J.P., Lee, S., Lester, J.C.: Story-based learning: the impact of narrative on learning experiences and outcomes. In: Woolf, B.P., Aïmeur, E., Nkambou, R., Lajoie, S. (eds.) ITS 2008. LNCS, vol. 5091, pp. 530–539. Springer, Heidelberg (2008). doi:10.1007/978-3-540-69132-7_56
Min, W., Ha, E., Rowe, J., Mott, B., Lester, J.: Deep learning-based goal recognition in open-ended digital games. In: Proceedings of the AAAI Conference on Artificial Intelligence and Interactive Digital Entertainment (AIIDE) (2014)
Oh, J., Meneguzzi, F., Sycara, K., Norman, T.: ANTIPA: an agent architecture for intelligent information assistance. In: Proceedings of the European Conference on Artificial Intelligence (ECAI), pp. 1055–1056 (2010)
Oh, J., Meneguzzi, F., Sycara, K., Norman, T.: An agent architecture for prognostic reasoning assistance. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 2513–2518 (2011)
Oh, J., Meneguzzi, F., Sycara, K., Norman, T.: Probabilistic plan recognition for intelligent information agents: towards proactive software assistant agents. In: Proceedings of the International Conference on Agents and Artificial Intelligence (ICAART), pp. 281–287 (2011)
Raghavan, T.E.S.: Finite-step algorithms for single-controller and perfect information stochastic games. In: Neyman, A., Sorin, S. (eds.) Stochastic Games and Applications. NATO Science Series (Series C: Mathematical and Physical Sciences), vol. 570, pp. 227–251. Springer, Netherlands (2003). doi:10.1007/978-94-010-0189-2_15
Ramírez, M., Geffner, H.: Plan recognition as planning. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 1778–1783 (2009)
Ramírez, M., Geffner, H.: Probabilistic plan recognition using off-the-shelf classical planners. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI), pp. 1121–1126 (2010)
Ramírez, M., Geffner, H.: Goal recognition over POMDPs: inferring the intention of a POMDP agent. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI), pp. 2009–2014 (2011)
Schmidt, C., Sridharan, N., Goodson, J.: The plan recognition problem: an intersection of psychology and artificial intelligence. Artif. Intell. 11(1–2), 45–83 (1978)
Son, T.C., Sabuncu, O., Schulz-Hanke, C., Schaub, T., Yeoh, W.: Solving goal recognition design using ASP. In: Proceedings of the AAAI Conference on Artificial Intelligence (AAAI) (2016)
Sukthankar, G., Geib, C., Bui, H.H., Pynadath, D., Goldman, R.P.: Plan, Activity, and Intent Recognition: Theory and Practice. Newnes, Boston (2014)
Tavakkoli, A., Kelley, R., King, C., Nicolescu, M., Nicolescu, M., Bebis, G.: A vision-based architecture for intent recognition. In: Proceedings of the International Symposium on Advances in Visual Computing, pp. 173–182 (2007)
Vilain, M.: Getting serious about parsing plans: a grammatical analysis of plan recognition. In: Proceedings of the National Conference on Artificial Intelligence (AAAI), pp. 190–197 (1990)
Wayllace, C., Hou, P., Yeoh, W., Son, T.C.: Goal recognition design with stochastic agent action outcomes. In: Proceedings of the International Joint Conference on Artificial Intelligence (IJCAI) (2016)
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2017 Springer International Publishing AG
About this paper
Cite this paper
Ang, S., Chan, H., Jiang, A.X., Yeoh, W. (2017). Game-Theoretic Goal Recognition Models with Applications to Security Domains. In: Rass, S., An, B., Kiekintveld, C., Fang, F., Schauer, S. (eds) Decision and Game Theory for Security. GameSec 2017. Lecture Notes in Computer Science(), vol 10575. Springer, Cham. https://doi.org/10.1007/978-3-319-68711-7_14
Download citation
DOI: https://doi.org/10.1007/978-3-319-68711-7_14
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-319-68710-0
Online ISBN: 978-3-319-68711-7
eBook Packages: Computer ScienceComputer Science (R0)