{"type":"ScholarlyArticle","title":"Learning to Infer Final Plans in Human Team Planning","authors":[{"name":"Joseph Kim","slug":"joseph-kim","given":"Joseph","family":"Kim","affiliation":"Computer Science and Artificial Intelligence Laboratory , Massachusetts Institute of Technology; {joseph"},{"name":"Matthew E. Woicik","slug":"matthew-e-woicik","given":"Matthew E.","family":"Woicik","affiliation":"Computer Science and Artificial Intelligence Laboratory , Massachusetts Institute of Technology; {joseph"},{"name":"Matthew C. Gombolay","slug":"matthew-c-gombolay","given":"Matthew C.","family":"Gombolay","affiliation":"MIT Lincoln Laboratory * , Lexington , MA"},{"name":"Sung-Hyun Son","slug":"sung-hyun-son","given":"Sung-Hyun","family":"Son","affiliation":"MIT Lincoln Laboratory * , Lexington , MA"},{"name":"Julie A. Shah","slug":"julie-a-shah","given":"Julie A.","family":"Shah","affiliation":"Computer Science and Artificial Intelligence Laboratory , Massachusetts Institute of Technology; {joseph"}],"abstract":"We envision an intelligent agent that analyzes conversations during human team meetings in order to infer the team’s plan, with the purpose of providing decision support to strengthen that plan. We present a novel learning technique to infer teams' final plans directly from a processed form of their planning conversation. Our method employs reinforcement learning to train a model that maps features of the discussed plan and patterns of dialogue exchange among participants to a final, agreed-upon plan. We employ planning domain models to efficiently search the large space of possible plans, and the costs of candidate plans serve as the reinforcement signal. We demonstrate that our technique successfully infers plans within a variety of challenging domains, with higher accuracy than prior art. With our domain-independent feature set, we empirically demonstrate that our model trained on one planning domain can be applied to successfully infer team plans within a novel planning domain.","doi":"10.24963/ijcai.2018/663","url":"https://ijcai.org/proceedings/2018/663","pdf":"https://ijcai.org/proceedings/2018/0663.pdf","markdown":"https://ijcai.org/proceedings/2018/663.md","bibtex":"https://ijcai.org/proceedings/2018/bibtex/663","volume":{"slug":"2018","title":"Proceedings of the Twenty-Seventh International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2018","url":"https://ijcai.org/proceedings/2018/","year":2018,"location":"Stockholm","dates":"13-19 July 2018","editors":"Jérôme Lang","isbn":"978-0-9992411-2-7","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2018"},"section":"Planning and Scheduling","track":"Main track","number":663,"pages":{"first":4771,"last":4779},"keywords":["Humans and AI: Human-AI Collaboration","Planning and Scheduling: Applications of Planning","Planning and Scheduling: Activity and Plan Recognition"],"videos":[],"references":[{"position":1,"raw":"[Amir and Gal, 2013] Ofra Amir and Ya'akov Kobi Gal. Plan recognition and visualization in exploratory learning environments. ACM Trans. Interactive Intelligent Systems, 3(3):16, 2013.","title":"Plan recognition and visualization in exploratory learning environments","authors":"Gal ; ] Ofra Amir, Ya'akov Kobi Amir, Gal","year":"2013","venue":"ACM Trans. Interactive Intelligent Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Artzi and Zettlemoyer, 2013] Yoav Artzi and Luke Zettle- moyer. Weakly supervised learning of semantic parsers for mapping instructions to actions. Trans. ACL, 1:49-62, 2013.","title":"Weakly supervised learning of semantic parsers for mapping instructions to actions","authors":"Zettlemoyer Artzi","year":"2013","venue":"Trans. ACL","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Banerjee et al., 2010] Bikramjit Banerjee, Landon Krae- mer, and Jeremy Lyle. Multi-agent plan recognition: for- malization and algorithms. In AAAI, pages 1059-1064, 2010.","title":"Multi-agent plan recognition: formalization and algorithms","authors":"Bikramjit Banerjee, Landon Kraemer, Jeremy Lyle","year":"2010","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Branavan et al., 2012] SRK Branavan, Nate Kushman, Tao Lei, and Regina Barzilay. Learning high-level planning from text. In ACL, pages 126-135, 2012.","title":"Learning high-level planning from text","authors":"Branavan","year":"2012","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":5,"raw":"[Bylander, 1991] Tom Bylander. Complexity results for planning. In IJCAI, pages 274-279, 1991.","title":"Complexity results for planning","authors":"Tom Bylander, Bylander","year":"1991","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/1991/41"},{"position":6,"raw":"[Carberry, 1990] Sandra Carberry. Plan Recognition in Nat- ural Language Dialogue. MIT Press, 1990.","title":"Plan Recognition in Natural Language Dialogue","authors":"Sandra Carberry","year":"1990","venue":null,"doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Carberry, 2001] Sandra Carberry. Techniques for plan recognition. User Modeling and User-Adapted Interac- tion, 11(1):31-48, 2001.","title":"Techniques for plan recognition","authors":"Sandra Carberry","year":"2001","venue":"User Modeling and User-Adapted Interaction","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Carletta, 2007] Jean Carletta. Unleashing the killer corpus: experiences in creating the multi-everything AMI meeting corpus. Language Resources and Evaluation, 41(2):181- 190, 2007.","title":"Unleashing the killer corpus: experiences in creating the multi-everything AMI meeting corpus","authors":"Carletta ;, Jean Carletta","year":"2007","venue":"Language Resources and Evaluation","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Casper and Murphy, 2003] Jennifer Casper and Robin R. Murphy. Human-robot interactions during the robot- assisted urban search and rescue response at the world trade center. IEEE Trans. SMC, Part B, 33(3):367-385, 2003.","title":"Human-robot interactions during the robotassisted urban search and rescue response at the world trade center","authors":"Jennifer Casper, Robin R Murphy","year":"2003","venue":"IEEE Trans. SMC, Part B","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Di Eugenio et al., 2000] Barbara Di Eugenio, Pamela W Jordan, Richmond H Thomason, and Johanna D Moore. The agreement process: An empirical investigation of human-human computer-mediated collaborative dialogs. Int. Jour. Hum.-Com. Studies, 53(6):1017-1076, 2000.","title":"The agreement process: An empirical investigation of human-human computer-mediated collaborative dialogs","authors":"Barbara Di, Eugenio, Pamela W Jordan, Richmond H Thomason, Johanna D Moore","year":"2000","venue":"Int. Jour. Hum.-Com. Studies","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Freedman et al., 2014] Richard G Freedman, Hee-Tae Jung, and Shlomo Zilberstein. Plan and activity recognition from a topic modeling perspective. In ICAPS, pages 360-364, 2014.","title":"Plan and activity recognition from a topic modeling perspective","authors":"Hee-Tae Richard G Freedman, Shlomo Jung, Zilberstein","year":"2014","venue":"ICAPS","doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Gerevini and Long, 2005] Alfonso Gerevini and Derek Long. Plan constraints and preferences in PDDL3. Fifth IPC. Tech. Rep., 2005.","title":"Plan constraints and preferences in PDDL3","authors":"Alfonso Gerevini, Derek Long","year":"2005","venue":"Fifth IPC","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Gombolay et al., 2017] Matthew Gombolay, Reed Jensen, and Sung-Hyun Song. Machine learning techniques for analyzing training behavior in serious gaming. IEEE Trans. on Computational Intelligence and AI in Games, 2017.","title":"Machine learning techniques for analyzing training behavior in serious gaming","authors":"Matthew Gombolay, Reed Jensen, Sung-Hyun Song","year":"2017","venue":"IEEE Trans. on Computational Intelligence and AI in Games","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Gupta and Lehal, 2010] Vishal Gupta and Gurpreet Singh Lehal. A survey of text summarization extractive tech- niques. Jour. Emerg. Tech. in Web Intelligence, 2(3):258- 268, 2010.","title":"A survey of text summarization extractive techniques","authors":"Vishal Gupta, Gurpreet Singh, Lehal","year":"2010","venue":"Jour. Emerg. Tech. in Web Intelligence","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Hoffmann et al., 2004] Jörg Hoffmann, Julie Porteous, and Laura Sebastia. Ordered landmarks in planning. JAIR, 22:215-278, 2004.","title":"Ordered landmarks in planning","authors":"Hoffmann","year":"2004","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Hoffmann, 2003] Jörg Hoffmann. The Metric-FF planning system: Translating \"ignoring delete lists\" to numeric state variables. JAIR, 20:291-341, 2003.","title":"The Metric-FF planning system: Translating \"ignoring delete lists\" to numeric state variables","authors":"Jörg Hoffmann","year":"2003","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Kaminka et al., 2002] Gal A Kaminka, David V Pynadath, and Milind Tambe. Monitoring teams by overhearing: A multi-agent plan-recognition approach. JAIR, 17(1):83- 135, 2002.","title":"Monitoring teams by overhearing: A multi-agent plan-recognition approach","authors":"Kaminka","year":"2002","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Katz et al., 2018] Michael Katz, Shirin Sohrabi, Octavian Udrea, and Dominik Winterer. A novel iterative approach to top-k planning. In ICAPS, 2018.","title":"A novel iterative approach to top-k planning","authors":"Michael Katz, Shirin Sohrabi, Octavian Udrea, Dominik Winterer","year":"2018","venue":"ICAPS","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Kim and Shah, 2016] Joseph Kim and Julie A Shah. Im- proving team's consistency of understanding in meetings. IEEE Trans. Human-Machine Systems, 46(5):625-637, 2016.","title":"Improving team's consistency of understanding in meetings","authors":"Joseph Kim, Julie A Shah","year":"2016","venue":"IEEE Trans. Human-Machine Systems","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Kim et al., 2015] Been Kim, Caleb M Chacha, and Julie A Shah. Inferring team task plans from human meetings: A generative modeling approach with logic-based prior. JAIR, 52:361-398, 2015.","title":"Inferring team task plans from human meetings: A generative modeling approach with logic-based prior","authors":"Kim","year":"2015","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Lafferty et al., 2001] John Lafferty, Andrew McCallum, and Fernando C.N. Pereira. Conditional random fields: Probabilistic models for segmenting and labeling sequence data. In ICML, pages 282-289, 2001.","title":"Conditional random fields: Probabilistic models for segmenting and labeling sequence data","authors":"John Lafferty, Andrew Mccallum, Fernando C N Pereira","year":"2001","venue":"ICML","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Larson et al., 1996] James R Larson, Caryn Christensen, Ann S Abbott, and Timothy M Franz. Diagnosing groups: charting the flow of information in medical decision- making teams. Jour. Personality and Social Psychology, 71(2):315, 1996.","title":"Diagnosing groups: charting the flow of information in medical decisionmaking teams","authors":"Caryn James R Larson, Ann S Christensen, Timothy M Abbott, Franz","year":"1996","venue":"Jour. Personality and Social Psychology","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Miller, 2004] C. Miller. Modeling human workload limita- tions on multiple UAV control. In Human Factors, pages 526-527, 2004.","title":"Modeling human workload limitations on multiple UAV control","authors":"C Miller","year":"2004","venue":"Human Factors","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Pereira et al., 2017] Ramon Fraga Pereira, Nir Oren, and Felipe Meneguzzi. Landmark-based heuristics for goal recognition. In AAAI, pages 3622 -3628, 2017.","title":"Landmark-based heuristics for goal recognition","authors":"Ramon Fraga Pereira, Nir Oren, Felipe Meneguzzi","year":"2017","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Qin et al., 2017] Kechen Qin, Lu Wang, and Joseph Kim. Joint modeling of content and discourse relations in dia- logues. In ACL, pages 974-984, 2017.","title":"Joint modeling of content and discourse relations in dialogues","authors":"Qin","year":"2017","venue":"ACL","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Ramırez and Geffner, 2009] Miquel Ramırez and Hector Geffner. Plan recognition as planning. In IJCAI, pages 1778-1783, 2009.","title":"Plan recognition as planning","authors":"Geffner Ramırez, Miquel Ramırez, Hector Geffner","year":"2009","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2009/296"},{"position":27,"raw":"[Richter and Westphal, 2010] Silvia Richter and Matthias Westphal. The LAMA planner: Guiding cost-based any- time planning with landmarks. JAIR, 39:127-177, 2010.","title":"The LAMA planner: Guiding cost-based anytime planning with landmarks","authors":"Westphal Richter, Silvia Richter, Matthias Westphal","year":"2010","venue":"JAIR","doi":null,"url":null,"internal_url":null},{"position":28,"raw":"[Sohrabi et al., 2016] Shirin Sohrabi, Anton V Riabov, and Octavian Udrea. Plan recognition as planning revisited. In IJCAI, pages 3258-3264, 2016.","title":"Plan recognition as planning revisited","authors":"Shirin Sohrabi, Anton V Riabov, Octavian Udrea","year":"2016","venue":"IJCAI","doi":null,"url":null,"internal_url":"/proceedings/2016/461"},{"position":29,"raw":"[Somasundaran and Wiebe, 2007] Swapna Somasundaran and Janyce Wiebe. Detecting arguing and sentiment in meetings. In SIGdial Workshop on Discourse and Dialogue, 2007.","title":"Detecting arguing and sentiment in meetings","authors":"Wiebe Somasundaran, Swapna Somasundaran, Janyce Wiebe","year":"2007","venue":"SIGdial Workshop on Discourse and Dialogue","doi":null,"url":null,"internal_url":null},{"position":30,"raw":"[Sukthankar and Sycara, 2006] Gita Sukthankar and Katia Sycara. Simultaneous team assignment and behavior recognition from spatio-temporal agent traces. In AAAI, 2006.","title":"Simultaneous team assignment and behavior recognition from spatio-temporal agent traces","authors":"Sycara Sukthankar, Gita Sukthankar, Katia Sycara","year":"2006","venue":"AAAI","doi":null,"url":null,"internal_url":null},{"position":31,"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 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":"NIPS","doi":null,"url":null,"internal_url":null},{"position":32,"raw":"[Vered et al., 2018] Mor Vered, Ramon Fraga Pereira, Mauricio Magnaguagno, Felipe Meneguzzi, and Gal A. Kaminka. Towards online goal recognition combining goal mirroring and landmarks. In AAMAS, 2018.","title":"Towards online goal recognition combining goal mirroring and landmarks","authors":"Mor Vered, Ramon Fraga Pereira, Mauricio Magnaguagno, Felipe Meneguzzi, Gal A Kaminka","year":"2018","venue":"AAMAS","doi":null,"url":null,"internal_url":null},{"position":33,"raw":"[Zhuo and Kambhampati, 2013] Hankz Hankui Zhuo and Subbarao Kambhampati. Action-model acquisition from noisy plan traces. In IJCAI, pages 2444-2450, 2013.","title":"Hankz Hankui Zhuo and Subbarao Kambhampati. Action-model acquisition from noisy plan traces","authors":"Kambhampati Zhuo","year":"2013","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":34,"raw":"[Zhuo and Li, 2011] Hankz Hankui Zhuo and Lei Li. Multi- agent plan recognition with partial team traces and plan libraries. In IJCAI, pages 484-489, 2011.","title":"Lei Li. Multiagent plan recognition with partial team traces and plan libraries","authors":"Li ; ] Zhuo, Hankui Hankz, Zhuo","year":"2011","venue":"IJCAI","doi":null,"url":null,"internal_url":null},{"position":35,"raw":"[Zhuo et al., 2012] Hankz Hankui Zhuo, Qiang Yang, and Subbarao Kambhampati. Action-model based multi-agent plan recognition. In NIPS, pages 368-376, 2012.","title":"Action-model based multi-agent plan recognition","authors":"Zhuo","year":"2012","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":36,"raw":"[Zhuo et al., 2013] Hankz Hankui Zhuo, Tuan Anh Nguyen, and Subbarao Kambhampati. Model-lite case-based plan- ning. In AAAI, pages 1077-1083, 2013.","title":"Model-lite case-based planning","authors":"Zhuo","year":"2013","venue":"AAAI","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}