Affect control processes: Intelligent affective interaction using a partially observable Markov decision process

@article{Hoey2013AffectCP,
  title={Affect control processes: Intelligent affective interaction using a partially observable Markov decision process},
  author={Jesse Hoey and Tobias Navarro Schr{\"o}der and Areej M. Alhothali},
  journal={Artif. Intell.},
  year={2013},
  volume={230},
  pages={134-172}
}

Deliberative and Affective Reasoning: a Bayesian Dual-Process Model

This paper provides a high-level view of dual process theories and advances BayesAct as a plausible, computationally tractable model based in social-psychological and sociological theory.

Agents with Affective Traits for Decision-Making in Complex Environments

Recent events have probably lead us to wonder why people make decisions that seem to be irrational, and that go against any easily understandable logic. The fact that these decisions are emotionally

Computational Affective Model of Human Action in a Social Dilemma

Affect Control Theory (ACT) is a powerful and general sociological model of human affective interaction [6]. It provides an empirically derived mathematical model of culturally shared sentiments as

Intelligent Affect: Rational Decision Making for Socially Aligned Agents

Planning in BayesAct allows one to go beyond the affective prescription, and leads to the emergence of more complex interactions between "cognitive" and "affective" reasoning, such as deception leading to manipulation and altercasting.

Monte-Carlo Planning for Socially Aligned Agents using Bayesian Affect Control Theory

A continuous variant of a successful Monte-Carlo tree search planner (POMCP), which performs dynamic discretisation of the action and observation spaces while planning, and can be used in non-affective domains.

A Biologically-Inspired Neural Implementation of Affect Control Theory

NeuroACT, a neural computational model and implementation of a sociopsychological theory called Affect Control Theory is presented, to model the role of affect guiding decisionmaking in AI agents, resulting in interactions that are similar to human interactions, while inhibiting some behaviors based on the social context.

"Conservatives Overfit, Liberals Underfit": The Social-Psychological Control of Affect and Uncertainty

A revised BayesAct model is introduced that more deeply integrates social-psychological theorising, and a component of the model is demonstrated as being sufficient to account for cognitive biases about fairness, dissonance and conformity.

Continuous Affect Recognition with Different Features and Modeling Approaches in Evaluation-Potency-Activity Space

This thesis works on automatic affect recognition and compares three different types of feature descriptors with support vector machine regression (SVR) and bidirectional long short-term memory (BLSTM) to predict users’ emotions in three-dimensional space and integrates the affect recognition module into an iterated prisoner's dilemma game.

Socially Intelligent Affective AI

This doctoral research goal is to delve deeper into emotion in AI by surveying computational models implemented in AI that uses emotion in decision-making or behaviour, and to combine information about context, identities, behaviour and emotion in a social interaction scene to predict social incoherence and to recommend appropriate behaviour.

From Affect Theoretical Foundations to Computational Models of Intelligent Affective Agents

This work identifies and classify the main processes and concepts which can be used in a generic affective computational model, and proposes a theoretical framework that includes all these processes and concept that a model of an affective agent with practical reasoning could use.
...

References

SHOWING 1-10 OF 115 REFERENCES

Bayesian Affect Control Theory

This work forms a probabilistic and decision theoretic model of the same underlying principles, and shows this to be a generalisation of the basic theory of Affect Control Theory, which allows the model to generate affectively believable interactions with people by learning about their identity and predicting their behaviours.

Monte-Carlo Planning for Socially Aligned Agents using Bayesian Affect Control Theory

A continuous variant of a successful Monte-Carlo tree search planner (POMCP), which performs dynamic discretisation of the action and observation spaces while planning, and can be used in non-affective domains.

Affectively Aligned Cognitive Assistance Using Bayesian Affect Control Theory

A novel emotionally intelligent cognitive assistant to engage and help older adults with Alzheimer’s disease (AD) to complete activities of daily living (ADL) more independently.

Empirically building and evaluating a probabilistic model of user affect

This paper illustrates how the predictive part of the affective model is built by combining general theories with empirical studies to adapt the theories to the target application domain and presents results on the model’s accuracy, showing that the model achieves good accuracy on several of the target emotions.

FLAME—Fuzzy Logic Adaptive Model of Emotions

This paper proposes a new computational model of emotions that can be incorporated into intelligent agents and other complex, interactive programs and demonstrates empirically through a computer simulation of a pet that the adaptive components of the model are crucial to users' assessments of the believability of the agent's interactions.

Can a rational agent afford to be affectless? a formal approach

It is suggested that emotions and rationality are closely linked in the human mind and, therefore, need to be included in architectures for designing rational artificial agents, whether these agents are to interact with humans, to model humans' behaviors and actions, or both.

Bayesian Affect Control Theory of Self

A Bayesian generalization of the sociological affect control theory of self is proposed, allowing it to be multi-modal, uncertain, and learnable (agents can learn the identities and selves of other agents).

A domain-independent framework for modeling emotion

Affective Computing

Key issues in affective computing, " computing that relates to, arises from, or influences emotions", are presented and new applications are presented for computer-assisted learning, perceptual information retrieval, arts and entertainment, and human health and interaction.

HED: A Computational Model of Affective Adaptation and Emotion Dynamics

  • J. Steephen
  • Psychology
    IEEE Transactions on Affective Computing
  • 2013
A modified exponentially weighted average computational model of affective adaptation, which predicts its time course and the resulting affective dynamics, is presented and it is shown that the model is consistent with several previously reported characteristics of Affective dynamics.
...