Intelligent Affect: Rational Decision Making for Socially Aligned Agents

Nabiha Asghar, Jesse Hoey
Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, PMLR R13:69-78, 2015.

Abstract

Affect Control Theory (ACT) is a mathematical model that makes accurate predictions about human behaviour across a wide range of settings. The predictions, which are derived from statistics about human actions and identities in real and laboratory environments, are shared prescriptive and affective behaviours that are believed to lead to solutions to everyday cooperative problems. A generalisation of ACT, called BayesACT, allows the principles of ACT to be used for human-interactive agents by combining a probabilistic version of the ACT dynamical model of affect with a utility function encoding external goals. Planning in BayesACT, which we address in this paper, then allows one to go beyond the affective prescription, and leads to the emergence of more complex interactions between “cognitive” reasoning and “affective” reasoning, such as deception leading to manipulation and altercasting. We use a continuous variant of a successful Monte-Carlo tree search planner (POMCP), which performs dynamic discretisation of the action and observation spaces while planning. We present results on two classic two-person social dilemmas, and show how reasoning about affect can produce some remarkably powerful, yet human-like, strategies in these games.

Cite this Paper

BibTeX
@InProceedings{pmlr-vR13-asghar15a, title = {Intelligent Affect: Rational Decision Making for Socially Aligned Agents}, author = {Asghar, Nabiha and Hoey, Jesse}, booktitle = {Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence}, pages = {69--78}, year = {2015}, editor = {Meila, Marina and Heskes, Tom}, volume = {R13}, series = {Proceedings of Machine Learning Research}, month = {12--16 Jul}, publisher = {PMLR}, pdf = {https://raw.githubusercontent.com/mlresearch/r13/main/assets/asghar15a/asghar15a.pdf}, url = {https://proceedings.mlr.press/r13/asghar15a.html}, abstract = {Affect Control Theory (ACT) is a mathematical model that makes accurate predictions about human behaviour across a wide range of settings. The predictions, which are derived from statistics about human actions and identities in real and laboratory environments, are shared prescriptive and affective behaviours that are believed to lead to solutions to everyday cooperative problems. A generalisation of ACT, called BayesACT, allows the principles of ACT to be used for human-interactive agents by combining a probabilistic version of the ACT dynamical model of affect with a utility function encoding external goals. Planning in BayesACT, which we address in this paper, then allows one to go beyond the affective prescription, and leads to the emergence of more complex interactions between “cognitive” reasoning and “affective” reasoning, such as deception leading to manipulation and altercasting. We use a continuous variant of a successful Monte-Carlo tree search planner (POMCP), which performs dynamic discretisation of the action and observation spaces while planning. We present results on two classic two-person social dilemmas, and show how reasoning about affect can produce some remarkably powerful, yet human-like, strategies in these games.}, note = {Reissued by PMLR on 04 October 2026.} }
Endnote
%0 Conference Paper %T Intelligent Affect: Rational Decision Making for Socially Aligned Agents %A Nabiha Asghar %A Jesse Hoey %B Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence %C Proceedings of Machine Learning Research %D 2015 %E Marina Meila %E Tom Heskes %F pmlr-vR13-asghar15a %I PMLR %P 69--78 %U https://proceedings.mlr.press/r13/asghar15a.html %V R13 %X Affect Control Theory (ACT) is a mathematical model that makes accurate predictions about human behaviour across a wide range of settings. The predictions, which are derived from statistics about human actions and identities in real and laboratory environments, are shared prescriptive and affective behaviours that are believed to lead to solutions to everyday cooperative problems. A generalisation of ACT, called BayesACT, allows the principles of ACT to be used for human-interactive agents by combining a probabilistic version of the ACT dynamical model of affect with a utility function encoding external goals. Planning in BayesACT, which we address in this paper, then allows one to go beyond the affective prescription, and leads to the emergence of more complex interactions between “cognitive” reasoning and “affective” reasoning, such as deception leading to manipulation and altercasting. We use a continuous variant of a successful Monte-Carlo tree search planner (POMCP), which performs dynamic discretisation of the action and observation spaces while planning. We present results on two classic two-person social dilemmas, and show how reasoning about affect can produce some remarkably powerful, yet human-like, strategies in these games. %Z Reissued by PMLR on 04 October 2026.
APA
Asghar, N. & Hoey, J.. (2015). Intelligent Affect: Rational Decision Making for Socially Aligned Agents. Proceedings of the 31st Conference on Uncertainty in Artificial Intelligence, in Proceedings of Machine Learning Research R13:69-78 Available from https://proceedings.mlr.press/r13/asghar15a.html. Reissued by PMLR on 04 October 2026.

Related Material