research-article

Open access

Acting as Inverse Inverse Planning

Authors:

Kartik Chandra,

Joshua Tenenbaum,

Jonathan Ragan-KelleyAuthors Info & Claims

SIGGRAPH '23: ACM SIGGRAPH 2023 Conference Proceedings

Article No.: 7, Pages 1 - 12

https://doi.org/10.1145/3588432.3591510

Published: 23 July 2023 Publication History

All formats PDF

Abstract

Great storytellers know how to take us on a journey. They direct characters to act—not necessarily in the most rational way—but rather in a way that leads to interesting situations, and ultimately creates an impactful experience for audience members looking on.

If audience experience is what matters most, then can we help artists and animators directly craft such experiences, independent of the concrete character actions needed to evoke those experiences? In this paper, we offer a novel computational framework for such tools. Our key idea is to optimize animations with respect to simulated audience members’ experiences. To simulate the audience, we borrow an established principle from cognitive science: that human social intuition can be modeled as “inverse planning,” the task of inferring an agent’s (hidden) goals from its (observed) actions. Building on this model, we treat storytelling as “inverse inverse planning,” the task of choosing actions to manipulate an inverse planner’s inferences. Our framework is grounded in literary theory, naturally capturing many storytelling elements from first principles. We give a series of examples to demonstrate this, with supporting evidence from human subject studies.

Supplemental Material

M4V File

Supplemental code nad video

Download
92.15 MB

MP4 File

presentation

Download
157.22 MB

ZIP File

Supplemental code nad video

Download
714.83 KB

References

[1]

Saurabh Arora and Prashant Doshi. 2021. A survey of inverse reinforcement learning: Challenges, methods and progress. Artificial Intelligence 297 (2021), 103500. https://arxiv.org/pdf/1806.06877

[2]

Byung-Chull Bae and R Michael Young. 2008. A use of flashback and foreshadowing for surprise arousal in narrative using a plan-based approach. In Joint international conference on interactive digital storytelling. Springer, 156–167. https://www.academia.edu/download/30704103/icids1.pdf

Digital Library

[3]

Chris L Baker, Noah D Goodman, and Joshua B Tenenbaum. 2008. Theory-based social goal inference. In Proceedings of the thirtieth annual conference of the cognitive science society. Citeseer, 1447–1452. http://cocolab.stanford.edu/papers/BakerEtAl2008-Cogsci.pdf

[4]

Chris L Baker, Rebecca Saxe, and Joshua B Tenenbaum. 2009. Action understanding as inverse planning. Cognition 113, 3 (2009), 329–349. https://www.sciencedirect.com/science/article/pii/S0010027709001607

[5]

Chris L Baker, Joshua B Tenenbaum, and Rebecca R Saxe. 2007. Goal inference as inverse planning. In Proceedings of the Annual Meeting of the Cognitive Science Society, Vol. 29. https://escholarship.org/content/qt5v06n97q/qt5v06n97q.pdf

[6]

Peter W Battaglia, Jessica B Hamrick, and Joshua B Tenenbaum. 2013. Simulation as an engine of physical scene understanding. Proceedings of the National Academy of Sciences 110, 45 (2013), 18327–18332. https://www.pnas.org/doi/full/10.1073/pnas.1306572110

[7]

Richard Bellman. 1966. Dynamic programming. Science 153, 3731 (1966), 34–37.

[8]

Justine Cassell, Hannes Högni Vilhjálmsson, and Timothy Bickmore. 2001. BEAT: The Behavior Expression Animation Toolkit. In Proceedings of the 28th Annual Conference on Computer Graphics and Interactive Techniques. Association for Computing Machinery, New York, NY, USA, 477–486. https://doi.org/10.1145/383259.383315

Digital Library

[9]

Kartik Chandra, Tzu-Mao Li, Joshua Tenenbaum, and Jonathan Ragan-Kelley. 2022. Designing Perceptual Puzzles by Differentiating Probabilistic Programs. In Special Interest Group on Computer Graphics and Interactive Techniques Conference Proceedings (SIGGRAPH ’22 Conference Proceedings). https://doi.org/10.1145/3528233.3530715

Digital Library

[10]

Yun-Gyung Cheong and R Michael Young. 2006. A Computational Model of Narrative Generation for Suspense. In AAAI. 1906–1907. https://www.aaai.org/Papers/Workshops/2006/WS-06-04/WS06-04-003.pdf

[11]

Anca D Dragan. 2015. Legible robot motion planning. Ph. D. Dissertation. Carnegie Mellon University. https://www.ri.cmu.edu/pub_files/2015/6/A_Dragan_Robotics_2015.pdf

[12]

Frédo Durand, Maneesh Agrawala, Bruce Gooch, Victoria Interrante, Victor Ostromoukhov, and Denis Zorin. 2002. Perceptual and artistic principles for effective computer depiction. SIGGRAPH 2002 Course# 13 Notes (2002). http://people.csail.mit.edu/fredo/SIG02_ArtScience/DepictionNotes2.pdf

[13]

John Funge, Xiaoyuan Tu, and Demetri Terzopoulos. 1999. Cognitive modeling: Knowledge, reasoning and planning for intelligent characters. In Proceedings of the 26th annual conference on Computer graphics and interactive techniques. 29–38. https://dl.acm.org/doi/pdf/10.1145/311535.311538

Digital Library

[14]

Richard J Gerrig and Allan BI Bernardo. 1994. Readers as problem-solvers in the experience of suspense. Poetics 22, 6 (1994), 459–472. https://www.sciencedirect.com/science/article/pii/0304422X94900213/pdf?md5=4e88a66f151c18e279f030fa56cba285&pid=1-s2.0-0304422X94900213-main.pdf

[15]

Noah D Goodman and Michael C Frank. 2016. Pragmatic language interpretation as probabilistic inference. Trends in cognitive sciences 20, 11 (2016), 818–829. http://cocolab.stanford.edu/papers/GoodmanFrank2016-TICS.pdf

[16]

Barbara Hayes-Roth, Robert van Gent, and Daniel Huber. 1997. Acting in character. Creating personalities for synthetic actors (1997), 92–112. https://citeseerx.ist.psu.edu/viewdoc/summary?doi=10.1.1.84.5760

[17]

Fritz Heider and Marianne Simmel. 1944. An experimental study of apparent behavior. The American journal of psychology 57, 2 (1944), 243–259. https://www.jstor.org/stable/pdf/1416950.pdf

[18]

Mark K Ho, Fiery Cushman, Michael L Littman, and Joseph L Austerweil. 2021. Communication in action: Planning and interpreting communicative demonstrations.Journal of Experimental Psychology: General (2021). https://psyarxiv.com/a8sxk/

[19]

Mark K Ho, Rebecca Saxe, and Fiery Cushman. 2022. Planning with theory of mind. Trends in Cognitive Sciences (2022). https://saxelab.mit.edu/sites/default/files/publications/HoSaxeCushman2022.pdf

[20]

Sean Dae Houlihan, Desmond Ong, Maddie Cusimano, and Rebecca Saxe. 2022. Reasoning about the antecedents of emotions: Bayesian causal inference over an intuitive theory of mind. In Proceedings of the Annual Meeting of the Cognitive Science Society, Vol. 44. https://escholarship.org/content/qt7sn3w3n2/qt7sn3w3n2.pdf

[21]

Marcell Jankovics. 1974. Sisyphus. https://www.youtube.com/watch?v=vyZK8rkeqPM

[22]

Mubbasir Kapadia, Seth Frey, Alexander Shoulson, Robert W Sumner, and Markus H Gross. 2016. CANVAS: computer-assisted narrative animation synthesis. In Symposium on Computer Animation. 199–209. https://people.cs.rutgers.edu/ mk1353/pdfs/2016-sca-canvas.pdf

[23]

Dilan Patrick Kiley, Andrew J Reagan, Lewis Mitchell, Christopher M Danforth, and Peter Sheridan Dodds. 2016. Game story space of professional sports: Australian rules football. Physical Review E 93, 5 (2016), 052314. https://cdanfort.w3.uvm.edu/research/2016-kiley-pre.pdf

[24]

Mykel J Kochenderfer, Tim A Wheeler, and Kyle H Wray. 2022. Algorithms for decision making. MIT press. https://algorithmsbook.com

[25]

Max Kreminski and Chris Martens. 2022. Unmet Creativity Support Needs in Computationally Supported Creative Writing. In Proceedings of the First Workshop on Intelligent and Interactive Writing Assistants (In2Writing 2022). https://doi.org/10.18653/v1/2022.in2writing-1.11

[26]

Karin Kukkonen. 2014. Bayesian narrative: Probability, plot and the shape of the fictional world. Anglia 132, 4 (2014), 720–739. https://www.duo.uio.no/bitstream/handle/10852/54629/1/01%2BKukkonen%2BBayesian%2BNarrative.pdf

[27]

Brenda Laurel. 1986. Toward the design of a computer-based interactive fantasy system. Ph. D. Dissertation. The Ohio State University. https://etd.ohiolink.edu/apexprod/rws_etd/send_file/send?accession=osu1487265143146814&disposition=inline

[28]

Michael Lebowitz. 1985. Story-telling as planning and learning. Poetics 14, 6 (1985), 483–502. https://academiccommons.columbia.edu/doi/10.7916/D8K362MH/download

[29]

Aaron B Loyall. 1997. Believable Agents: Building Interactive Personalities.Technical Report. Carnegie Mellon University, Department of Computer Science. https://apps.dtic.mil/sti/pdfs/ADA327862.pdf

[30]

Manasi Malik and Leyla Isik. 2022. Social Inference from Relational Visual Information. Journal of Vision 22, 14 (2022), 3810–3810. https://jov.arvojournals.org/article.aspx?articleid=2784648

[31]

Chris Martens, Anne-Gwenn Bosser, Joao F Ferreira, and Marc Cavazza. 2013. Linear logic programming for narrative generation. In International Conference on Logic Programming and Nonmonotonic Reasoning. Springer, 427–432.

Digital Library

[32]

Michael Mateas. 1999. An Oz-centric review of interactive drama and believable agents. In Artificial intelligence today. Springer, 297–328. https://citeseerx.ist.psu.edu/viewdoc/download?doi=10.1.1.47.9259&rep=rep1&type=pdf

Digital Library

[33]

Michael Mateas and Andrew Stern. 2003. Façade: An experiment in building a fully-realized interactive drama. In Game developers conference, Vol. 2. 4–8. https://www.cc.gatech.edu/fac/Charles.Isbell/classes/reading/papers/MateasSternGDC03.pdf

[34]

James R Meehan. 1977. TALE-SPIN, An Interactive Program that Writes Stories. In Ijcai, Vol. 77. 91–98. https://www.ijcai.org/Proceedings/77-1/Papers/013.pdf

[35]

Aviv Netanyahu, Tianmin Shu, Boris Katz, Andrei Barbu, and Joshua B Tenenbaum. 2021. PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception. In Proceedings of the AAAI Conference on Artificial Intelligence, Vol. 35. 845–853. https://www.tshu.io/PHASE/PHASE.pdf

[36]

Andrew Y Ng, Stuart Russell, 2000. Algorithms for inverse reinforcement learning. In ICML, Vol. 1. 2. http://www.datascienceassn.org/sites/default/files/Algorithms%20for%20Inverse%20Reinforcement%20Learning.pdf

[37]

Desmond C Ong, Harold Soh, Jamil Zaki, and Noah D Goodman. 2019a. Applying probabilistic programming to affective computing. IEEE Transactions on Affective Computing 12, 2 (2019), 306–317. https://arxiv.org/pdf/1903.06445.pdf

Digital Library

[38]

Desmond C Ong, Jamil Zaki, and Noah D Goodman. 2015. Affective cognition: Exploring lay theories of emotion. Cognition 143 (2015), 141–162. https://www.sciencedirect.com/sdfe/reader/pii/S0010027715300196/pdf

[39]

Desmond C Ong, Jamil Zaki, and Noah D Goodman. 2019b. Computational models of emotion inference in theory of mind: A review and roadmap. Topics in cognitive science 11, 2 (2019), 338–357. https://onlinelibrary.wiley.com/doi/pdf/10.1111/tops.12371

[40]

Kunal Pattanayak, Vikram Krishnamurthy, and Christopher Berry. 2022. Inverse-Inverse Reinforcement Learning. How to Hide Strategy from an Adversarial Inverse Reinforcement Learner. arXiv preprint arXiv:2205.10802 (2022). https://arxiv.org/pdf/2205.10802

[41]

Ken Perlin and Athomas Goldberg. 1996. Improv: A System for Scripting Interactive Actors in Virtual Worlds. In Proceedings of the 23rd Annual Conference on Computer Graphics and Interactive Techniques(SIGGRAPH ’96). Association for Computing Machinery, New York, NY, USA, 205–216. https://doi.org/10.1145/237170.237258

Digital Library

[42]

Madison L Pesowski, Alyssa D Quy, Michelle Lee, and Adena Schachner. 2020. Children use inverse planning to detect social transmission in design of artifacts. In Proceedings of the Annual Conference of the Cognitive Science Society. https://cognitivesciencesociety.org/cogsci20/papers/0150/0150.pdf

[43]

Claudio S Pinhanez. 1999. Representation and recognition of action in interactive spaces. Ph. D. Dissertation. Massachusetts Institute of Technology. https://dspace.mit.edu/handle/1721.1/62342

[44]

Yingdong Qian, Marta Kryven, Tao Gao, Hanbyul Joo, and Josh Tenenbaum. 2021. Modeling human intention inference in continuous 3D domains by inverse planning and body kinematics. arXiv e-prints (2021), arXiv–2112. https://social-intelligence-human-ai.github.io/docs/camready_12.pdf

[45]

Setayesh Radkani, Josh Tenenbaum, and Rebecca Saxe. 2022. Modeling punishment as a rational communicative social action. In Proceedings of the Annual Meeting of the Cognitive Science Society, Vol. 44. https://escholarship.org/content/qt47g8d89h/qt47g8d89h.pdf

[46]

Deepak Ramachandran and Eyal Amir. 2007. Bayesian Inverse Reinforcement Learning. In IJCAI, Vol. 7. 2586–2591. https://www.aaai.org/Papers/IJCAI/2007/IJCAI07-416.pdf

[47]

Andrew J Reagan, Lewis Mitchell, Dilan Kiley, Christopher M Danforth, and Peter Sheridan Dodds. 2016. The emotional arcs of stories are dominated by six basic shapes. EPJ Data Science 5, 1 (2016), 1–12. https://epjdatascience.springeropen.com/articles/10.1140/epjds/s13688-016-0093-1

[48]

Mark Owen Riedl and R Michael Young. 2004. An intent-driven planner for multi-agent story generation. In Autonomous Agents and Multiagent Systems, International Joint Conference on, Vol. 2. IEEE Computer Society, 186–193. https://www.academia.edu/download/30704104/025_riedlm_story.pdf

[49]

Mark O Riedl and Robert Michael Young. 2010. Narrative planning: Balancing plot and character. Journal of Artificial Intelligence Research 39 (2010), 217–268. https://www.jair.org/index.php/jair/article/download/10669/25501

Digital Library

[50]

Daniel Rousseau and Barbara Hayes-Roth. 1998. A Social-Psychological Model for Synthetic Actors. In Proceedings of the Second International Conference on Autonomous Agents (Minneapolis, Minnesota, USA) (AGENTS ’98). Association for Computing Machinery, New York, NY, USA, 165–172. https://doi.org/10.1145/280765.280795

Digital Library

[51]

Rebecca Saxe and Sean Dae Houlihan. 2017. Formalizing emotion concepts within a Bayesian model of theory of mind. Current opinion in Psychology 17 (2017), 15–21. https://daeh.info/assets/pubs/saxe2017cop.pdf

[52]

Patrick Shafto, Noah D Goodman, and Thomas L Griffiths. 2014. A rational account of pedagogical reasoning: Teaching by, and learning from, examples. Cognitive psychology 71 (2014), 55–89. https://www.sciencedirect.com/science/article/pii/S0010028514000024

[53]

Hubert PH Shum, Taku Komura, and Shuntaro Yamazaki. 2010. Simulating multiple character interactions with collaborative and adversarial goals. IEEE Transactions on Visualization and Computer Graphics 18, 5 (2010), 741–752. https://ieeexplore.ieee.org/document/5669299

Digital Library

[54]

Nicolas Szilas. 2003. IDtension: a narrative engine for Interactive Drama. In Proceedings of the technologies for interactive digital storytelling and entertainment (TIDSE) conference.

[55]

Sean Tauber and Mark Steyvers. 2011. Using inverse planning and theory of mind for social goal inference. In Proceedings of the Annual Meeting of the Cognitive Science Society, Vol. 33. https://cogsci.mindmodeling.org/2011/papers/0585/paper0585.pdf

[56]

Frank Thomas, Ollie Johnston, and Frank Thomas. 1995. The illusion of life: Disney animation. Hyperion New York. https://archive.org/details/TheIllusionOfLifeDisneyAnimation/

[57]

Tomer Ullman, Chris Baker, Owen Macindoe, Owain Evans, Noah Goodman, and Joshua Tenenbaum. 2009. Help or hinder: Bayesian models of social goal inference. Advances in neural information processing systems 22 (2009). https://www.tomerullman.org/papers/nips2010.pdf

[58]

Kurt Vonnegut. 2005. A Man Without a Country. Seven Stories Press.

[59]

Kevin Wampler, Erik Andersen, Evan Herbst, Yongjoon Lee, and Zoran Popović. 2010. Character Animation in Two-Player Adversarial Games. ACM Trans. Graph. 29, 3, Article 26 (jul 2010), 13 pages. https://doi.org/10.1145/1805964.1805970

Digital Library

[60]

Peter Weyhrauch. 1997. Guiding interactive drama. Carnegie Mellon University Pittsburgh. http://cs.engr.uky.edu/ sgware/reading/papers/weyhrauch1997guiding.pdf

Digital Library

[61]

Andrew Witkin and Michael Kass. 1988. Spacetime constraints. ACM Siggraph Computer Graphics 22, 4 (1988), 159–168. https://dl.acm.org/doi/pdf/10.1145/378456.378507

Digital Library

[62]

Jungdam Won, Deepak Gopinath, and Jessica Hodgins. 2021. Control Strategies for Physically Simulated Characters Performing Two-Player Competitive Sports. ACM Trans. Graph. 40, 4, Article 146 (jul 2021), 11 pages. https://doi.org/10.1145/3450626.3459761

Digital Library

[63]

Jungdam Won, Kyungho Lee, Carol O’Sullivan, Jessica K. Hodgins, and Jehee Lee. 2014. Generating and Ranking Diverse Multi-Character Interactions. ACM Trans. Graph. 33, 6, Article 219 (nov 2014), 12 pages. https://doi.org/10.1145/2661229.2661271

Digital Library

[64]

Jie Xu, Viktor Makoviychuk, Yashraj Narang, Fabio Ramos, Wojciech Matusik, Animesh Garg, and Miles Macklin. 2022. Accelerated policy learning with parallel differentiable simulation. ICLR (2022). https://arxiv.org/pdf/2204.07137.pdf

[65]

Erica J Yoon, Michael Henry Tessler, Noah D Goodman, and Michael C Frank. 2016. Talking with tact: Polite language as a balance between kindness and informativity. In Proceedings of the 38th annual conference of the cognitive science society. Cognitive Science Society, 2771–2776. http://socsci-dev.ss.uci.edu/ lpearl/courses/readings/YoonEtAl2016_Politeness.pdf

[66]

Tan Zhi-Xuan, Jordyn Mann, Tom Silver, Josh Tenenbaum, and Vikash Mansinghka. 2020. Online Bayesian Goal Inference for Boundedly Rational Planning Agents. Advances in Neural Information Processing Systems 33 (2020). https://arxiv.org/pdf/2006.07532.pdf

Cited By

Collins KSucholutsky IBhatt UChandra KWong LLee MZhang CZhi-Xuan THo MMansinghka VWeller ATenenbaum JGriffiths T(2024)Building machines that learn and think with peopleNature Human Behaviour10.1038/s41562-024-01991-98:10(1851-1863)Online publication date: 22-Oct-2024
https://doi.org/10.1038/s41562-024-01991-9
Chandra KChen TLi TRagan-Kelley JTenenbaum JOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Inferring the future by imagining the pastProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3667048(21196-21216)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3667048
Chandra KLi TTenenbaum JRagan‐Kelley J(2023) Storytelling as Inverse Inverse Planning Topics in Cognitive Science10.1111/tops.1271016:1(54-70)Online publication date: 14-Nov-2023
https://doi.org/10.1111/tops.12710

Index Terms

Acting as Inverse Inverse Planning
1. Computing methodologies
  1. Artificial intelligence
    1. Philosophical/theoretical foundations of artificial intelligence
      1. Cognitive science
      2. Theory of mind
  2. Computer graphics
    1. Animation
      1. Procedural animation

Recommendations

Planning and Interaction Levels for TV Storytelling
Interactive Storytelling
Abstract
Interactivity, coherence and diversity of the stories are key issues for the development of interactive storytelling systems. When stories are to be told via interactive TV, special interaction methods are also necessary in order to cope with high ...
Engaging theatre audiences before the play: the design of playful interactive storytelling experiences
Inputs-Outputs '13: Proceedings of the 2013 Inputs-Outputs Conference: An Interdisciplinary Conference on Engagement in HCI and Performance

In this paper I present Mobile Stories, a design-led project that explored ways of playfully motivating and engaging theatre audiences in their journey before the premiere of a theatrical play. The project used the art of storytelling and mobile ...
Conceiving ShapeShifting TV: a computational language for truly-interactive TV
EuroITV '07: Proceedings of the 5th European Conference on Interactive TV and Video

iTV does not yet have truly interactive programmes, that is programmes whose content adapts to the preferences of their viewers. In commercially deployed iTV productions, the programmes themselves are essentially linear and therefore non-interactive. In ...

Comments

Please enable JavaScript to view thecomments powered by Disqus.

Information & Contributors

Information

Published In

cover image ACM Conferences

SIGGRAPH '23: ACM SIGGRAPH 2023 Conference Proceedings

July 2023

911 pages

ISBN:9798400701597

DOI:10.1145/3588432

Copyright © 2023 Owner/Author.

This work is licensed under a Creative Commons Attribution International 4.0 License.

Sponsors

SIGGRAPH: ACM Special Interest Group on Computer Graphics and Interactive Techniques

Publisher

Association for Computing Machinery

New York, NY, United States

Publication History

Published: 23 July 2023

Check for updates

Author Tags

Qualifiers

Research-article
Research
Refereed limited

Funding Sources

ONR
NSF

Conference

SIGGRAPH '23

Sponsor:

SIGGRAPH

SIGGRAPH '23: Special Interest Group on Computer Graphics and Interactive Techniques Conference

August 6 - 10, 2023

CA, Los Angeles, USA

Acceptance Rates

Overall Acceptance Rate 1,822 of 8,601 submissions, 21%

Contributors

Other Metrics

View Article Metrics

Bibliometrics & Citations

Bibliometrics

Article Metrics

3
Total Citations
View Citations
1,245
Total Downloads

Downloads (Last 12 months)856
Downloads (Last 6 weeks)90

Reflects downloads up to 14 Nov 2024

Other Metrics

View Author Metrics

Citations

Cited By

Collins KSucholutsky IBhatt UChandra KWong LLee MZhang CZhi-Xuan THo MMansinghka VWeller ATenenbaum JGriffiths T(2024)Building machines that learn and think with peopleNature Human Behaviour10.1038/s41562-024-01991-98:10(1851-1863)Online publication date: 22-Oct-2024
https://doi.org/10.1038/s41562-024-01991-9
Chandra KChen TLi TRagan-Kelley JTenenbaum JOh ANaumann TGloberson ASaenko KHardt MLevine S(2023)Inferring the future by imagining the pastProceedings of the 37th International Conference on Neural Information Processing Systems10.5555/3666122.3667048(21196-21216)Online publication date: 10-Dec-2023
https://dl.acm.org/doi/10.5555/3666122.3667048
Chandra KLi TTenenbaum JRagan‐Kelley J(2023) Storytelling as Inverse Inverse Planning Topics in Cognitive Science10.1111/tops.1271016:1(54-70)Online publication date: 14-Nov-2023
https://doi.org/10.1111/tops.12710

View Options

View options

PDF

View or Download as a PDF file.

eReader

View online with eReader.

HTML Format

View this article in HTML Format.

Get Access

Login options

Check if you have access through your login credentials or your institution to get full access on this article.

Full Access

Get this Publication

Media

Figures

Other

Tables

View Table of Contents