{"type":"ScholarlyArticle","title":"Gradient-Based Mixed Planning with Symbolic and Numeric Action Parameters (Extended Abstract)","authors":[{"name":"Kebing Jin","slug":"kebing-jin","given":"Kebing","family":"Jin","affiliation":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"},{"name":"Hankz Hankui Zhuo","slug":"hankz-hankui-zhuo","given":"Hankz Hankui","family":"Zhuo","affiliation":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"},{"name":"Zhanhao Xiao","slug":"zhanhao-xiao","given":"Zhanhao","family":"Xiao","affiliation":"School of Computer Science , Guangdong Polytechnic Normal University , Guangzhou , China"},{"name":"Hai Wan","slug":"hai-wan","given":"Hai","family":"Wan","affiliation":"School of Computer Science and Engineering , Sun Yat-sen University , Guangzhou , China"},{"name":"Subbarao Kambhampati","slug":"subbarao-kambhampati","given":"Subbarao","family":"Kambhampati","affiliation":"Department of Computer Science and Engineering , Arizona State University , US"}],"abstract":"Dealing with planning problems with both logical relations and numeric changes in real-world dynamic environments is challenging. Existing numeric planning systems for the problem often discretize numeric variables or impose convex constraints on numeric variables, which harms the performance when solving problems, especially when the problems contain obstacles and non-linear numeric effects. In this work, we propose a novel algorithm framework to solve numeric planning problems mixed with logical relations and numeric changes based on gradient descent. We cast the numeric planning with logical relations and numeric changes as an optimization problem. Specifically, we extend the syntax to allow parameters of action models to be either objects or real-valued numbers, which enhances the ability to model real-world numeric effects. Based on the extended modeling language, we propose a gradient-based framework to simultaneously optimize numeric parameters and compute appropriate actions to form candidate plans. The gradient-based framework is composed of an algorithmic heuristic module based on propositional operations to select actions and generate constraints for gradient descent, an algorithmic transition module to update states to the next ones, and a loss module to compute loss. We repeatedly minimize loss by updating numeric parameters and compute candidate plans until it converges into a valid plan for the planning problem.","doi":"10.24963/ijcai.2023/782","url":"https://ijcai.org/proceedings/2023/782","pdf":"https://ijcai.org/proceedings/2023/0782.pdf","markdown":"https://ijcai.org/proceedings/2023/782.md","bibtex":"https://ijcai.org/proceedings/2023/bibtex/782","volume":{"slug":"2023","title":"Proceedings of the Thirty-Second International Joint Conference on Artificial Intelligence","short_title":"IJCAI 2023","url":"https://ijcai.org/proceedings/2023/","year":2023,"location":"Macao, SAR","dates":"19-25 August 2023","editors":"Edith Elkind","isbn":"978-1-956792-03-4","publisher":"International Joint Conferences on Artificial Intelligence Organization","doi_prefix":"10.24963/ijcai.2023"},"section":"Journal Track","track":"Journal Track","number":782,"pages":{"first":6915,"last":6919},"keywords":["Planning and Scheduling: PS: Planning algorithms","Planning and Scheduling: PS: Mixed discrete/continuous planning"],"videos":[],"references":[{"position":1,"raw":"[Bajpai and Garg, 2018] Aniket Nick Bajpai and Sankalp Garg. Transfer of deep reactive policies for mdp planning. Advances in Neural Information Processing Systems, 31, 2018.","title":"Transfer of deep reactive policies for mdp planning","authors":"Nick Aniket, Sankalp Bajpai, Garg","year":"2018","venue":"Advances in Neural Information Processing Systems","doi":null,"url":null,"internal_url":null},{"position":2,"raw":"[Blum and Furst, 1997] Avrim Blum and Merrick L. Furst. Fast planning through planning graph analysis. Artif. In- tell., 90(1-2):281-300, 1997.","title":"Fast planning through planning graph analysis","authors":"Avrim Blum, Merrick L Furst","year":"1997","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":3,"raw":"[Coles et al., 2008] Andrew Coles, Maria Fox, Derek Long, and Amanda Smith. A hybrid relaxed planning graph'lp heuristic for numeric planning domains. In Proceedings of the Eighteenth International Conference on Automated Planning and Scheduling, ICAPS 2008, Sydney, Australia, September 14-18, 2008, pages 52-59, 2008.","title":"A hybrid relaxed planning graph'lp heuristic for numeric planning domains","authors":"Andrew Coles, Maria Fox, Derek Long, Amanda Smith","year":"2008","venue":"Proceedings of the Eighteenth International Conference on Automated Planning and Scheduling, ICAPS 2008","doi":null,"url":null,"internal_url":null},{"position":4,"raw":"[Cui and Khardon, 2016] Hao Cui and Roni Khardon. On- line symbolic gradient-based optimization for factored ac- tion mdps. In Subbarao Kambhampati, editor, Proceedings of the Twenty-Fifth International Joint Conference on Ar- tificial Intelligence, pages 3075-3081. IJCAI/AAAI Press, 2016.","title":"Online symbolic gradient-based optimization for factored action mdps","authors":"Hao Cui, Roni Khardon","year":"2016","venue":"Proceedings of the Twenty-Fifth International Joint Conference on Artificial Intelligence","doi":null,"url":null,"internal_url":"/proceedings/2016/436"},{"position":5,"raw":"[Eyerich et al., 2009] Patrick Eyerich, Robert Mattmüller, and Gabriele Röger. Using the context-enhanced addi- tive heuristic for temporal and numeric planning. In Al- fonso Gerevini, Adele E. Howe, Amedeo Cesta, and Ioan- nis Refanidis, editors, Proceedings of the 19th Interna- tional Conference on Automated Planning and Scheduling. AAAI, 2009.","title":"Using the context-enhanced additive heuristic for temporal and numeric planning","authors":"Patrick Eyerich, Robert Mattmüller, Gabriele Röger","year":"2009","venue":"Proceedings of the 19th International Conference on Automated Planning and Scheduling","doi":null,"url":null,"internal_url":null},{"position":6,"raw":"[Fernández-González et al., 2018] Enrique Fernández- González, Brian C. Williams, and Erez Karpas. Scotty- activity: Mixed discrete-continuous planning with convex optimization. J. Artif. Intell. Res., 62:579-664, 2018.","title":"Scottyactivity: Mixed discrete-continuous planning with convex optimization","authors":"Enrique Fernández-González, Brian C Williams, Erez Karpas","year":"2018","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":7,"raw":"[Fox and Long, 2003] Maria Fox and Derek Long. Pddl2. 1: An extension to pddl for expressing temporal planning do- mains. Journal of artificial intelligence research, 20:61- 124, 2003.","title":"Pddl2. 1: An extension to pddl for expressing temporal planning domains","authors":"Maria Fox, Derek Long","year":"2003","venue":"Journal of artificial intelligence research","doi":null,"url":null,"internal_url":null},{"position":8,"raw":"[Fox and Long, 2006] Maria Fox and Derek Long. Mod- elling mixed discrete-continuous domains for planning. J. Artif. Intell. Res., 27:235-297, 2006.","title":"Modelling mixed discrete-continuous domains for planning","authors":"Maria Fox, Derek Long","year":"2006","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":9,"raw":"[Garg et al., 2019] Sankalp Garg, Aniket Bajpai, et al. Size independent neural transfer for rddl planning. In Proceed- ings of the International Conference on Automated Plan- ning and Scheduling, volume 29, pages 631-636, 2019.","title":"Size independent neural transfer for rddl planning","authors":"Sankalp Garg, Aniket Bajpai","year":"2019","venue":"Proceedings of the International Conference on Automated Planning and Scheduling","doi":null,"url":null,"internal_url":null},{"position":10,"raw":"[Gerevini and Serina, 2002] Alfonso Gerevini and Ivan Se- rina. LPG: A planner based on local search for planning graphs with action costs. In Proceedings of the Sixth In- ternational Conference on Artificial Intelligence Planning Systems, pages 13-22, 2002.","title":"Alfonso Gerevini and Ivan Serina. LPG: A planner based on local search for planning graphs with action costs","authors":"Serina Gerevini","year":"2002","venue":"Proceedings of the Sixth International Conference on Artificial Intelligence Planning Systems","doi":null,"url":null,"internal_url":null},{"position":11,"raw":"[Hafner et al., 2020] Danijar Hafner, Timothy Lillicrap, Mo- hammad Norouzi, and Jimmy Ba. Mastering atari with discrete world models. arXiv preprint arXiv:2010.02193, 2020.","title":"Mastering atari with discrete world models","authors":"Hafner","year":"2020","venue":null,"doi":null,"url":null,"internal_url":null},{"position":12,"raw":"[Helmert, 2006] Malte Helmert. The fast downward plan- ning system. J. Artif. Intell. Res., 26:191-246, 2006.","title":"The fast downward planning system","authors":"Malte Helmert","year":"2006","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":13,"raw":"[Hoffmann, 2001] Jörg Hoffmann. FF: the fast-forward plan- ning system. AI Magazine, 22(3):57-62, 2001.","title":"FF: the fast-forward planning system","authors":"Jörg Hoffmann, Hoffmann","year":"2001","venue":"AI Magazine","doi":null,"url":null,"internal_url":null},{"position":14,"raw":"[Hoffmann, 2003] Jörg Hoffmann. The metric-ff planning system: Translating \"ignoring delete lists\" to numeric state variables. J. Artif. Intell. Res., 20:291-341, 2003.","title":"The metric-ff planning system: Translating \"ignoring delete lists\" to numeric state variables","authors":"Jörg Hoffmann, Hoffmann","year":"2003","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":15,"raw":"[Ivankovic et al., 2014] Franc Ivankovic, Patrik Haslum, Sylvie Thiébaux, Vikas Shivashankar, and Dana S. Nau. Optimal planning with global numerical state constraints. In Steve A. Chien, Minh Binh Do, Alan Fern, and Wheeler Ruml, editors, Proceedings of the Twenty-Fourth Interna- tional Conference on Automated Planning and Scheduling. AAAI, 2014.","title":"Optimal planning with global numerical state constraints","authors":"Ivankovic","year":"2014","venue":"Proceedings of the Twenty-Fourth International Conference on Automated Planning and Scheduling","doi":null,"url":null,"internal_url":null},{"position":16,"raw":"[Jin et al., 2022] Kebing Jin, Hankz Hankui Zhuo, Zhanhao Xiao, Hai Wan, and Subbarao Kambhampati. Gradient- based mixed planning with symbolic and numeric action parameters. Artif. Intell., 313:103789, 2022.","title":"Gradientbased mixed planning with symbolic and numeric action parameters","authors":"Jin","year":"2022","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":17,"raw":"[Keyder et al., 2014] Emil Ragip Keyder, Jörg Hoffmann, and Patrik Haslum. Improving delete relaxation heuris- tics through explicitly represented conjunctions. J. Artif. Intell. Res., 50:487-533, 2014.","title":"Improving delete relaxation heuristics through explicitly represented conjunctions","authors":"Keyder","year":"2014","venue":"J. Artif. Intell. Res","doi":null,"url":null,"internal_url":null},{"position":18,"raw":"[Li and Williams, 2008] Hui X. Li and Brian C. Williams. Generative planning for hybrid systems based on flow tubes. In Proceedings of the Eighteenth International Con- ference on Automated Planning and Scheduling, ICAPS 2008, Sydney, Australia, September 14-18, 2008, pages 206-213, 2008.","title":"Generative planning for hybrid systems based on flow tubes","authors":"Hui X Li, Brian C Williams","year":"2008","venue":"Proceedings of the Eighteenth International Conference on Automated Planning and Scheduling, ICAPS 2008","doi":null,"url":null,"internal_url":null},{"position":19,"raw":"[Pantke et al., 2014] Florian Pantke, Stefan Edelkamp, and Otthein Herzog. Planning with numeric key perfor- mance indicators over dynamic organizations of intelligent agents. In Jörg P. Müller, Michael Weyrich, and Ana L. C. Bazzan, editors, Multiagent System Technologies -12th German Conference, pages 138-155. Springer, 2014.","title":"Planning with numeric key performance indicators over dynamic organizations of intelligent agents","authors":"Pantke","year":"2014","venue":"Multiagent System Technologies -12th German Conference","doi":null,"url":null,"internal_url":null},{"position":20,"raw":"[Savas et al., 2016] Emre Savas, Maria Fox, Derek Long, and Daniele Magazzeni. Planning using actions with con- trol parameters. In ECAI, pages 1185-1193, 2016.","title":"Planning using actions with control parameters","authors":"Emre Savas, Maria Fox, Derek Long, Daniele Magazzeni","year":"2016","venue":"ECAI","doi":null,"url":null,"internal_url":null},{"position":21,"raw":"[Scala et al., 2016] Enrico Scala, Patrik Haslum, Sylvie Thiébaux, and Miquel Ramírez. Interval-based relaxation for general numeric planning. In ECAI, pages 655-663, 2016.","title":"Interval-based relaxation for general numeric planning","authors":"Enrico Scala, Patrik Haslum, Sylvie Thiébaux, Miquel Ramírez","year":"2016","venue":"ECAI","doi":null,"url":null,"internal_url":null},{"position":22,"raw":"[Wu et al., 2017] Ga Wu, Buser Say, and Scott Sanner. Scal- able planning with tensorflow for hybrid nonlinear do- mains. In NIPS, pages 6273-6283, 2017.","title":"Scalable planning with tensorflow for hybrid nonlinear domains","authors":"Ga Wu, Buser Say, Scott Sanner","year":"2017","venue":"NIPS","doi":null,"url":null,"internal_url":null},{"position":23,"raw":"[Zhuo and Kambhampati, 2017] Hankz Hankui Zhuo and Subbarao Kambhampati. Model-lite planning: Case-based vs. model-based approaches. Artif. Intell., 246:1-21, 2017.","title":"Hankz Hankui Zhuo and Subbarao Kambhampati. Model-lite planning: Case-based vs. model-based approaches","authors":"Kambhampati Zhuo","year":"2017","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":24,"raw":"[Zhuo and Yang, 2014] Hankz Hankui Zhuo and Qiang Yang. Action-model acquisition for planning via transfer learning. Artif. Intell., 212:80-103, 2014.","title":"Action-model acquisition for planning via transfer learning","authors":"Yang ; ] Zhuo, Hankui Hankz, Qiang Zhuo, Yang","year":"2014","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":25,"raw":"[Zhuo et al., 2010] Hankz Hankui Zhuo, Qiang Yang, Derek Hao Hu, and Lei Li. Learning complex action mod- els with quantifiers and logical implications. Artif. Intell., 174(18):1540-1569, 2010.","title":"Learning complex action models with quantifiers and logical implications","authors":"Zhuo","year":"2010","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null},{"position":26,"raw":"[Zhuo et al., 2014] Hankz Hankui Zhuo, Héctor Muñoz- Avila, and Qiang Yang. Learning hierarchical task network domains from partially observed plan traces. Artif. Intell., 212:134-157, 2014.","title":"Learning hierarchical task network domains from partially observed plan traces","authors":"Zhuo","year":"2014","venue":"Artif. Intell","doi":null,"url":null,"internal_url":null}],"license_note":"Copyright International Joint Conferences on Artificial Intelligence."}