{"type":"ScholarlyArticle","title":"Evolutionary Approach to Security Games with Signaling","authors":[{"name":"Adam Żychowski","slug":"adam-zychowski","given":"Adam","family":"Żychowski","affiliation":"Faculty of Mathematics and Information Science , Warsaw University of Technology"},{"name":"Jacek Mańdziuk","slug":"jacek-mandziuk","given":"Jacek","family":"Mańdziuk","affiliation":"Faculty of Mathematics and Information Science , Warsaw University of Technology"},{"name":"Elizabeth Bondi","slug":"elizabeth-bondi","given":"Elizabeth","family":"Bondi","affiliation":"Center for Research on Computation and Society , Harvard University"},{"name":"Aravind Venugopal","slug":"aravind-venugopal","given":"Aravind","family":"Venugopal","affiliation":"Robert Bosch Centre for Data Science and AI , IIT Madras"},{"name":"Milind Tambe","slug":"milind-tambe","given":"Milind","family":"Tambe","affiliation":"Center for Research on Computation and Society , Harvard University"},{"name":"Balaraman Ravindran","slug":"balaraman-ravindran","given":"Balaraman","family":"Ravindran","affiliation":"Robert Bosch Centre for Data Science and AI , IIT Madras; Department of Computer Science and Engineering , IIT Madras"}],"abstract":"Green Security Games have become a popular way to model scenarios involving the protection of natural resources, such as wildlife. Sensors (e.g. drones equipped with cameras) have also begun to play a role in these scenarios by providing real-time information.\r\nIncorporating both human and sensor defender resources strategically is the  subject of recent work on Security Games with Signaling (SGS). However, current methods to solve SGS do not scale well in terms of time or memory.\r\nWe therefore propose a novel approach to SGS, which, for the first time in this domain, employs an Evolutionary Computation paradigm: EASGS. EASGS effectively searches the huge SGS solution space via suitable solution encoding in a chromosome and a specially-designed set of operators. The operators include three types of mutations, each focusing on a particular aspect of the SGS solution, optimized crossover and a local coverage improvement scheme (a memetic aspect of EASGS). We also introduce a new set of benchmark games, based on dense or locally-dense graphs that reflect real-world SGS settings.\r\nIn the majority of 342 test game instances, EASGS outperforms state-of-the-art methods, including a reinforcement learning method, in terms of time scalability, nearly constant memory utilization, and quality of the returned defender's strategies (expected payoffs).","doi":"10.24963/ijcai.2022/88","url":"https://ijcai.org/proceedings/2022/88","pdf":"https://ijcai.org/proceedings/2022/0088.pdf","markdown":"https://ijcai.org/proceedings/2022/88.md","bibtex":"https://ijcai.org/proceedings/2022/bibtex/88","volume":{"slug":"2022","title":"Proceedings of the Thirty-First International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2022","url":"https://ijcai.org/proceedings/2022/","year":2022,"location":"Vienna","dates":"23-29 July 2022","editors":"Luc De Raedt","isbn":"978-1-956792-00-3","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2022"},"section":"Agent-based and Multi-agent Systems","track":"Main Track","number":88,"pages":{"first":620,"last":627},"keywords":["Search: Evolutionary Computation","Agent-based and Multi-agent Systems: Noncooperative Games"],"videos":[{"label":"Video #1","url":"https://slideslive.com/38986734","length_sec":87,"provider":"slideslive"},{"label":"Video #2","url":"https://slideslive.com/38984877","length_sec":301,"provider":"slideslive"}],"references":[{"position":1,"raw":"[Basilico and Gatti, 2014] Nicola Basilico and Nicola Gatti. Strategic guard placement for optimal response to alarms in security games. In Proceedings of the 13th AAMAS, pages 1481-1482, 2014.","title":"Strategic guard placement for optimal response to alarms in security games","authors":"Nicola Basilico, Nicola Gatti","year":"2014","venue":"Proceedings of the 13th AAMAS","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Basilico et al., 2015] Nicola Basilico, Giuseppe De Nittis, and Nicola Gatti. A security game model for environment protection in the presence of an alarm system. In Interna- tional Conference on Decision and Game Theory for Se- curity, pages 192-207, 2015.","title":"A security game model for environment protection in the presence of an alarm system","authors":"Nicola Basilico, Giuseppe De Nittis, Nicola Gatti","year":"2015","venue":"International Conference on Decision and Game Theory for Security","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Basilico et al., 2016] Nicola Basilico, Giuseppe De Nittis, and Nicola Gatti. A security game combining patrolling and alarm-triggered responses under spatial and detection uncertainties. In Proceedings of the 30th AAAI, pages 397- 403, 2016.","title":"A security game combining patrolling and alarm-triggered responses under spatial and detection uncertainties","authors":"Nicola Basilico, Giuseppe De Nittis, Nicola Gatti","year":"2016","venue":"Proceedings of the 30th AAAI","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Basilico et al., 2017] Nicola Basilico, Giuseppe De Nittis, and Nicola Gatti. Adversarial patrolling with spatially un- certain alarm signals. Artificial Intelligence, pages 220- 257, 2017.","title":"Adversarial patrolling with spatially uncertain alarm signals","authors":"Nicola Basilico, Giuseppe De Nittis, Nicola Gatti","year":"2017","venue":"Artificial Intelligence","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bondi et al., 2018] Elizabeth Bondi, Fei Fang, Mark Hamil- ton, Debarun Kar, Donnabell Dmello, Jongmoo Choi, Robert Hannaford, Arvind Iyer, Lucas Joppa, Milind Tambe, et al. Spot poachers in action: Augmenting conser- vation drones with automatic detection in near real time. In Proceedings of the 32nd AAAI, pages 7741-7746, 2018.","title":"Spot poachers in action: Augmenting conservation drones with automatic detection in near real time","authors":"Elizabeth Bondi, Fei Fang, Mark Hamilton, Debarun Kar, Donnabell Dmello, Jongmoo Choi, Robert Hannaford, Arvind Iyer, Lucas Joppa, Milind Tambe","year":"2018","venue":"Proceedings of the 32nd AAAI","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Bondi et al., 2020] Elizabeth Bondi, Hoon Oh, Haifeng Xu, Fei Fang, Bistra Dilkina, and Milind Tambe. To signal or not to signal: Exploiting uncertain real-time information in signaling games for security and sustainability. In Pro- ceedings of the 34th AAAI, pages 1369-1377, 2020.","title":"To signal or not to signal: Exploiting uncertain real-time information in signaling games for security and sustainability","authors":"Elizabeth Bondi, Hoon Oh, Haifeng Xu, Fei Fang, Bistra Dilkina, Milind Tambe","year":"2020","venue":"Proceedings of the 34th AAAI","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Conitzer and Sandholm, 2006] Vincent Conitzer and Tuo- mas Sandholm. Computing the optimal strategy to commit to. In Proceedings of the 7th ACM Conference on Elec- tronic commerce, pages 82-90, 2006.","title":"Computing the optimal strategy to commit to","authors":"Sandholm Conitzer, Vincent Conitzer, Tuomas Sandholm","year":"2006","venue":"Proceedings of the 7th ACM Conference on Electronic commerce","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[de Cote et al., 2013] Enrique de Cote, Ruben Stranders, Nicola Basilico, Nicola Gatti, and Nick Jennings. Intro- ducing alarms in adversarial patrolling games. In Proceed- ings of the 12th AAMAS, pages 1275-1276, 2013.","title":"Introducing alarms in adversarial patrolling games","authors":"Enrique De Cote, Ruben Stranders, Nicola Basilico, Nicola Gatti, Nick Jennings","year":"2013","venue":"Proceedings of the 12th AAMAS","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[De Nittis and Gatti, 2018] Giuseppe De Nittis and Nicola Gatti. Facing multiple attacks in adversarial pa- trolling games with alarmed targets. arXiv preprint arXiv:1806.07111, 2018.","title":"Facing multiple attacks in adversarial patrolling games with alarmed targets","authors":"De Nittis, Giuseppe De Gatti, Nicola Nittis, Gatti","year":"2018","venue":null,"doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Fang et al., 2015] Fei Fang, Peter Stone, and Milind Tambe. When security games go green: Designing defender strate- gies to prevent poaching and illegal fishing. In Proceed- ings of the 24th IJCAI, pages 2589-2595, 2015.","title":"When security games go green: Designing defender strategies to prevent poaching and illegal fishing","authors":"Fei Fang, Peter Stone, Milind Tambe","year":"2015","venue":"Proceedings of the 24th IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2015/367"},{"position":11,"raw":"[Karwowski et al., 2019] Jan Karwowski, Jacek Mańdziuk, Adam Żychowski, Filip Grajek, and Bo An. A memetic approach for sequential security games on a plane with moving targets. In Proceedings of the 33rd AAAI, pages 970-977, 2019.","title":"A memetic approach for sequential security games on a plane with moving targets","authors":"Karwowski","year":"2019","venue":"Proceedings of the 33rd AAAI","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Leitmann, 1978] George Leitmann. On generalized Stack- elberg strategies. Journal of Optimization Theory and Ap- plications, 26(4):637-643, 1978.","title":"On generalized Stackelberg strategies","authors":"George Leitmann","year":"1978","venue":"Journal of Optimization Theory and Applications","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Sutton et al., 2000] Richard S Sutton, David A McAllester, Satinder P Singh, and Yishay Mansour. Policy gradient methods for reinforcement learning with function approx- imation. In Advances in NIPS, pages 1057-1063, 2000.","title":"Policy gradient methods for reinforcement learning with function approximation","authors":"David A Richard S Sutton, Mcallester, P Satinder, Yishay Singh, Mansour","year":"2000","venue":"Advances in NIPS","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Van Hasselt et al., 2016] Hado Van Hasselt, Arthur Guez, and David Silver. Deep reinforcement learning with dou- ble q-learning. In Proceedings of the 30th AAAI, pages 2094-2100, 2016.","title":"Deep reinforcement learning with double q-learning","authors":"Van Hasselt","year":"2016","venue":"Proceedings of the 30th AAAI","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Venugopal et al., 2021] Aravind Venugopal, Elizabeth Bondi, Harshavardhan Kamarthi, Keval Dholakia, Balara- man Ravindran, and Milind Tambe. Reinforcement learning for unified allocation and patrolling in signaling games with uncertainty. In Proceedings of the 20th AAMAS, pages 1353-1361, 2021.","title":"Reinforcement learning for unified allocation and patrolling in signaling games with uncertainty","authors":"Aravind Venugopal, Elizabeth Bondi, Harshavardhan Kamarthi, Keval Dholakia, Balaraman Ravindran, Milind Tambe","year":"2021","venue":"Proceedings of the 20th AAMAS","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Wang et al., 2019] Yufei Wang, Zheyuan Ryan Shi, Lantao Yu, Yi Wu, Rohit Singh, Lucas Joppa, and Fei Fang. Deep reinforcement learning for green security games with real- time information. In Proceedings of the 33rd AAAI, pages 1401-1408, 2019.","title":"Deep reinforcement learning for green security games with realtime information","authors":"Yufei Wang, Zheyuan, Ryan Shi, Lantao Yu, Yi Wu, Rohit Singh, Lucas Joppa, Fei Fang","year":"2019","venue":"Proceedings of the 33rd AAAI","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Xu et al., 2018] Haifeng Xu, Kai Wang, Phebe Vayanos, and Milind Tambe. Strategic coordination of human pa- trollers and mobile sensors with signaling for security games. In Proceedings of the 32nd AAAI, pages 1290- 1297, 2018.","title":"Strategic coordination of human patrollers and mobile sensors with signaling for security games","authors":"Haifeng Xu, Kai Wang, Phebe Vayanos, Milind Tambe","year":"2018","venue":"Proceedings of the 32nd AAAI","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Xu et al., 2020] Lily Xu, Shahrzad Gholami, Sara Mc Carthy, Bistra Dilkina, Andrew Plumptre, Milind Tambe, et al. Stay ahead of poachers: Illegal wildlife poaching prediction and patrol planning under uncertainty with field test evaluations. In 36th IEEE Conference on Data Engineering, pages 1898-1901, 2020.","title":"Stay ahead of poachers: Illegal wildlife poaching prediction and patrol planning under uncertainty with field test evaluations","authors":"Lily Xu, Shahrzad Gholami, Sara Mc Carthy, Bistra Dilkina, Andrew Plumptre, Milind Tambe","year":"2020","venue":"36th IEEE Conference on Data Engineering","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Yang et al., 2014] Rong Yang, Benjamin Ford, Milind Tambe, and Andrew Lemieux. Adaptive resource allo- cation for wildlife protection against illegal poachers. In Proceedings of the 13th AAMAS, pages 453-460, 2014.","title":"Adaptive resource allocation for wildlife protection against illegal poachers","authors":"Rong Yang, Benjamin Ford, Milind Tambe, Andrew Lemieux","year":"2014","venue":"Proceedings of the 13th AAMAS","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Żychowski and Mańdziuk, 2021a] Adam Żychowski and Jacek Mańdziuk. Evolution of strategies in sequential se- curity games. In Proceedings of the 20th AAMAS, pages 1434-1442, 2021.","title":"Adam Żychowski and Jacek Mańdziuk. Evolution of strategies in sequential security games","authors":"Mańdziuk Żychowski","year":"2021","venue":"Proceedings of the 20th AAMAS","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Żychowski and Mańdziuk, 2021b] Adam Żychowski and Jacek Mańdziuk. Learning attacker's bounded rationality model in security games. In International Conference on Neural Information Processing, volume 1516, pages 530- 539, 2021.","title":"Adam Żychowski and Jacek Mańdziuk. Learning attacker's bounded rationality model in security games","authors":"Mańdziuk Żychowski","year":"2021","venue":"International Conference on Neural Information Processing","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Żychowski et al., 2022] Adam Żychowski, Jacek Mańdziuk, Elizabeth Bondi, Aravind Venugopal, Milind Tambe, and Balaraman Ravindran. Evolutionary ap- proach to Security Games with signaling. arXiv preprint arXiv:2204.14173, 2022.","title":"Evolutionary approach to Security Games with signaling","authors":"Adam Żychowski, Jacek Mańdziuk, Elizabeth Bondi, Aravind Venugopal, Milind Tambe, Balaraman Ravindran","year":"2022","venue":null,"doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}