Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

Reason and Intuition01:37

Reason and Intuition

7.8K
The human brain processes information for decision-making using one of two routes: an intuitive system and a rational system (Epstein, 1994; popularized by Kahneman, 2011 as System 1 and System 2, respectively). The intuitive system is quick, impulsive, and operates with minimal effort, relying on emotions or habits to provide cues for what to do next, while the rational system is logical, analytical, deliberate, and methodical. Research in neuropsychology suggests that the...
7.8K
Impression Management Techniques III: Aligning Actions01:29

Impression Management Techniques III: Aligning Actions

215
Aligning actions are communicative strategies individuals employ to maintain social harmony and preserve personal identity in the face of potential disruptions to social norms. These actions are particularly important in managing social impressions when one's behavior might be seen as inappropriate, incompetent, or morally questionable.Types of Aligning ActionsThe three principal types of aligning actions are disclaimers, accounts, and apologies.DisclaimersDisclaimers are preventive; they are...
215
Automatic Processing and Automatic Social Behavior01:28

Automatic Processing and Automatic Social Behavior

367
Automatic processing refers to the cognitive operations that occur without conscious intent or awareness, playing a fundamental role in shaping social cognition and behavior. These processes enable individuals to navigate complex social environments efficiently by relying on mental shortcuts and pre-existing knowledge structures known as schemas. One of the most influential mechanisms underlying automatic processing is priming, which subtly activates mental representations through exposure to...
367
Implicit Personality Theories01:23

Implicit Personality Theories

704
Implicit personality theory explains how individuals make assumptions about the relationships between personality traits, behaviors, and character types. When people learn that someone possesses a particular trait, they tend to infer the presence of other related characteristics, forming a cohesive impression. This cognitive shortcut plays a crucial role in social interactions and interpersonal judgments.Central Traits and Their InfluenceSolomon Asch's seminal 1946 study highlighted the power...
704
Purposive Learning01:22

Purposive Learning

667
E. C. Tolman emphasized the purposiveness of behavior — the idea that much of our behavior is goal-directed. For instance, employees who aim for a promotion work diligently to meet their targets. Tolman argued that when classical conditioning and operant conditioning occur, the organism acquires certain expectations. In classical conditioning, a child might fear a dog because they expect it to bite. In operant conditioning, a person might consistently work overtime because they expect a...
667
Theory of Attribution I: Correspondent Inference Theory01:15

Theory of Attribution I: Correspondent Inference Theory

996
Correspondent inference theory, proposed by Jones and Davis in 1965, seeks to explain how individuals infer stable personality traits from observed behaviors. It suggests that people attribute actions to underlying dispositions rather than external circumstances, particularly when the behavior appears intentional and socially significant.Voluntary Behavior and Dispositional AttributionAccording to this theory, individuals are more likely to attribute behavior to personal traits when it appears...
996

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

The Aloe Family recipe for open and specialized healthcare LLMs.

NPJ digital medicine·2026
Same author

Design and validation of a responsible artificial intelligence-based system for the referral of diabetic retinopathy patients.

Health information science and systems·2025
Same author

Empirical antibiotic therapy improves outcomes in mechanically ventilated patients with COVID-19: An emulated targeted trial within a prospective, multicentre cohort study.

The Journal of infection·2025
Same author

Effects of intubation timing in patients with COVID-19 throughout the four waves of the pandemic: a matched analysis.

The European respiratory journal·2022
Same author

The ethical use of high-performance computing and artificial intelligence: fighting COVID-19 at Barcelona Supercomputing Center.

AI and ethics·2021
Same author

The Fourth-Revolution in the Water Sector Encounters the Digital Revolution.

Environmental science & technology·2020

Related Experiment Video

Updated: Apr 21, 2026

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

8.5K

Intentional policy graphs: A pipeline for explaining agent behavior through intentions.

Victor Gimenez-Abalos1, Sergio Alvarez-Napagao1,2, Adrian Tormos1

  • 1Barcelona Supercomputing Center, Plaça Eusebi Guell, 1-3, 08034 Barcelona, Spain.

Patterns (New York, N.Y.)
|April 20, 2026
PubMed
Summary

We developed intentional policy graphs to explain agent behavior in complex environments. This framework provides interpretable, intention-based explanations for AI decision-making, enhancing trust and understanding.

Keywords:
XAIagent explainabilityexplainable agencyintentionsinterpretabilitypost hoc explainabilityreliabilitytelic explanations

More Related Videos

Task Interruption and Resumption Paradigm for Testing the Activation and Pursuit of an Abstract Thinking Goal
06:45

Task Interruption and Resumption Paradigm for Testing the Activation and Pursuit of an Abstract Thinking Goal

Published on: April 18, 2017

6.7K
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

943

Related Experiment Videos

Last Updated: Apr 21, 2026

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses
05:21

Characterization of the Sense of Agency over the Actions of Neural-machine Interface-operated Prostheses

Published on: January 7, 2019

8.5K
Task Interruption and Resumption Paradigm for Testing the Activation and Pursuit of an Abstract Thinking Goal
06:45

Task Interruption and Resumption Paradigm for Testing the Activation and Pursuit of an Abstract Thinking Goal

Published on: April 18, 2017

6.7K
Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models
07:14

Virtual Agent for Real-Time Motivational Interviewing by Integrating Adaptive Nonverbal Behavior and Language Models

Published on: December 23, 2025

943

Area of Science:

  • Artificial Intelligence
  • Multi-Agent Systems
  • Explainable AI (XAI)

Background:

  • AI agents operate in complex environments with opaque decision-making.
  • Lack of transparency hinders trust, auditing, and human comprehension of AI behavior.

Purpose of the Study:

  • Introduce intentional policy graphs (IPGs) for post-hoc, model-agnostic explanation of agent behavior.
  • Provide telic explanations by inferring agent intentions from partial observations, moving beyond action-level descriptions.

Main Methods:

  • Extended policy graphs with a formal concept of intention.
  • Developed a construction pipeline, design principles, and quantitative metrics for interpretability and reliability trade-offs.
  • Applied the framework to a cooperative multi-agent game and real-world human driving data.

Main Results:

  • Intentions enable structured answers to 'what,' 'how,' and 'why' questions about agent behavior.
  • Demonstrated local and global explanation capabilities.
  • Showcased the framework's generality and explanatory power on diverse datasets without needing internal models.

Conclusions:

  • Intentional policy graphs offer a powerful method for explaining complex agent behavior.
  • The framework enhances transparency, trust, and understanding in AI systems.
  • IPGs provide a pathway to more interpretable and auditable AI decision-making processes.