# Acting as Inverse Inverse Planning

arXiv: https://arxiv.org/abs/2305.16913 · HTML: https://mlsanity.com/paper/2305.16913/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- Builds on 8 of its 67 references that are in the map.
- First posted on arXiv 26 May 2023.

## Builds on (most cited first, 8 of 8)

- [A Survey of Inverse Reinforcement Learning: Challenges, Methods and Progress](https://mlsanity.com/paper/1806.06877/) (2018)
- [Accelerated Policy Learning with Parallel Differentiable Simulation](https://mlsanity.com/paper/2204.07137/) (2022)
- [The emotional arcs of stories are dominated by six basic shapes](https://mlsanity.com/paper/1606.07772/) (2016)
- [Online Bayesian Goal Inference for Boundedly-Rational Planning Agents](https://mlsanity.com/paper/2006.07532/) (2020)
- [Narrative Planning: Balancing Plot and Character](https://mlsanity.com/paper/1401.3841/) (2014)
- [PHASE: PHysically-grounded Abstract Social Events for Machine Social Perception](https://mlsanity.com/paper/2103.01933/) (2021)
- [Designing Perceptual Puzzles by Differentiating Probabilistic Programs](https://mlsanity.com/paper/2204.12301/) (2022)
- [Applying Probabilistic Programming to Affective Computing](https://mlsanity.com/paper/1903.06445/) (2019)

## Built on by (most cited first, 5 of 5)

- [Building Machines that Learn and Think with People](https://mlsanity.com/paper/2408.03943/) (2024)
- [Differentiating Metropolis-Hastings to Optimize Intractable Densities](https://mlsanity.com/paper/2306.07961/) (2023)
- [Evaluating and Modeling Social Intelligence: A Comparative Study of Human and AI Capabilities](https://mlsanity.com/paper/2405.11841/) (2024)
- [Sketching With Your Voice: "Non-Phonorealistic" Rendering of Sounds via Vocal Imitation](https://mlsanity.com/paper/2409.13507/) (2024)
- [Visual Theory of Mind Enables the Invention of Proto-Writing](https://mlsanity.com/paper/2502.01568/) (2025)

## Abstract (arXiv)

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.