Action understanding as inverse planning

@article{Baker2009ActionUA,
  title={Action understanding as inverse planning},
  author={Chris L. Baker and Rebecca Saxe and Joshua B. Tenenbaum},
  journal={Cognition},
  year={2009},
  volume={113},
  pages={329-349}
}

Bayesian Theory of Mind

We present a computational framework for Theory of Mind (ToM): the human ability to make joint inferences about the unobservable beliefs and preferences underlying the observed actions of other

Inferring the intentional states of autonomous virtual agents

Computational Models of Mentalizing

TLDR
In this chapter, some of the innovations that have developed in economics, computer science, and cognitive neuroscience in modeling the computations underlying several mentalizing operations are reviewed.

Interpreting actions by attributing compositional desires

TLDR
By representing desires as probabilistic programs, an inverse planning model can infer complex desires underlying complex behaviors—desires with temporal and logical structure, which can be fulfilled in different ways.

Modeling Human Plan Recognition Using Bayesian Theory of Mind

Using Inverse Planning and Theory of Mind for Social Goal Inference

TLDR
It is found that observer models that incorporated inferences about agents’ beliefs outperformed an all-knowing observer model in describing human responses and that human responses were most consistent with the behavior of a model that incorporates information about both orientation and line-of-sight obstructions.

The intentional stance as structure learning: a computational perspective on mindreading

TLDR
It is proposed that humans use an intentional stance as a learning bias that sidesteps the (hard) structure learning problem and bootstraps the acquisition of generative models for others’ actions.

Mental state inference from indirect evidence through Bayesian event reconstruction

TLDR
This work presents a computational model of mental-state attribution that works by reconstructing the actions an agent took, based on the indirect evidence that revealed their presence, and quantitatively fits participant judgments, outperforming a simple alternative cue-based account.

Online Bayesian Goal Inference for Boundedly-Rational Planning Agents

TLDR
Experiments are presented showing that this modeling and inference architecture outperforms Bayesian inverse reinforcement learning baselines, accurately inferring goals from both optimal and non-optimal trajectories involving failure and back-tracking, while generalizing across domains with compositional structure and sparse rewards.
...

References

SHOWING 1-10 OF 96 REFERENCES

Bayesian models of human action understanding

TLDR
A Bayesian framework is presented for explaining how people reason about and predict the actions of an intentional agent, based on observing its behavior, and how this model can be used to infer the goal of an agent and predict how the agent will act in novel situations or when environmental constraints change.

Theory-based Social Goal Inference

Everyday human interaction relies on making inferences about social goals: goals that an intentional agent adopts in relation to another agent, such as “chasing”, “fleeing”, “approaching”,

Goal-Based Imitation as Probabilistic Inference over Graphical Models

TLDR
This paper shows that the problem of goal-based imitation can be formulated as one of inferring goals and selecting actions using a learned probabilistic graphical model of the environment, and describes algorithms for planning actions to achieve a goal state using Probabilistic inference.

Young children's reasoning about beliefs

One-year-old infants use teleological representations of actions productively

Taking the intentional stance at 12 months of age

Intuitive Theories of Mind: A Rational Approach to False Belief

We propose a rational analysis of children’s false belief reasoning. Our analysis realizes a continuous, evidencedriven transition between two causal Bayesian models of false belief. Both models

Infants' understanding of object-directed action

...