Canada

The introduction of large-scale data sets in psychology allows for more robust accounts of various cognitive mechanisms, one of which is human learning. However, these data sets provide participants with complete autonomy over their own participation in the task, and therefore require precisely studying the factors influencing dropout alongside learning. In this work, we present such a data set where 1,234,844 participants play 10,874,547 games of a challenging variant of tic-tac-toe. We establish that there is a correlation between task performance and total experience, and independently analyze participants’ dropout behavior and learning trajectories. We find evidence for stopping patterns as a function of playing strength and investigate the processes underlying playing strength increases with experience using a set of metrics derived from a planning model. Finally, we develop a joint model to account for both dropout and learning functions which replicates our empirical findings.

CogSci 2022

A joint analysis of dropout and learning functions in human decision-making with massive online data

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

The purpose of the AAAI conference series is to promote research in Artificial Intelligence (AI) and foster scientific exchange between researchers, practitioners, scientists, students, and engineers across the entirety of AI and its affiliated disciplines. AAAI-26 will feature technical paper presentations, special tracks, invited speakers, workshops, tutorials, poster sessions, senior member presentations, competitions, and exhibit programs, and a range of other activities to be announced.

To access this event page, you need to log in with the **email address you registered with**. Access credentials will be sent to your email from Underline - subject line "Welcome to AAAI 2026". Please be sure to check your spam email folder if you do not see an email confirmation right away.

Please log in

To access this event page, you are required to register.
Please complete your registration to continue.

We recommend reading [**the registration information**](https://aaai.org/conference/aaai/aaai-26/registration/) first.

**Online Registration Form**: https://aaai.getregistered.net/conference-2026 

Registration Required

AAAI 2026

We are pleased to announce the Fortieth AAAI Conference on Artificial Intelligence (AAAI-26), which will be held in Singapore EXPO from January 20 to January 27, 2026.

technical paper

Join us for CogSci2022! Our 44th Annual Conference will be centered around the theme of diversity, with an accompanying range of keynotes and invited speakers who themselves highlight the diversity of our field. Our three symposia are Cognition across Diverse Populations, Cognition within Diverse Societies, and Global Challenges for Cognitive Science. The conference is being offered in a fully hybrid environment for onsite and online attendees.
 
 [**The Program at a Glance can be found here**](https://cognitivesciencesociety.org/wp-content/uploads/2022/07/Cogsci-2022-PAAG-Detailed-July-12final-1.pdf)
 [**The Detailed Program can be found here**](https://cognitivesciencesociety.org/wp-content/uploads/2022/08/DeArmond-CogSci2022-program-v113-final.pdf)

This conference requires a registration to attend. Please use the link below to secure your ticket. The website will be available to all registered attendees on July 25th. 

[Register to Attend](https://cognitivesciencesociety.org/registration/)

Registration Is Required

The 44th Annual Meeting of the Cognitive Science Society highlighted research on the theme Cognitive Diversity in addition to the full breadth and diversity of research topics offered by the society’s membership. 





Joint pick and place tasks occur in many interpersonal scenarios, such as when two people pick up and pass dishes. Previous studies have demonstrated that low-dimensional models can accurately capture the dynamics of pick and place motor behaviors in a controlled 2D environment. The current study models the dynamics of pick-up and pass decisions within a less restrictive virtual reality mediated 3D joint pick and place task. Findings indicate that reach-normalized distance measures, between participants and objects/targets, could accurately predict pick-up and pass decisions. Findings also reveal that participants took longer to pick-up objects where division of labor boundaries were less obvious and tended to pass in locations maximizing the dyad’s efficiency. This study supports the notion that individuals are more likely to engage in interpersonal behavior when a task goal is perceived as difficult or unattainable (i.e., not afforded). Implications of findings for human-artificial agent interactions are discussed.

I Know Your Next Move: Action Decisions in Dyadic Pick and Place Tasks

There is a pressing need to inform the public and drive personal and political action to mitigate climate change. Recent theorizing suggests that people’s intuitive theories may be key levers for affecting attitude and behavior change (Weisman & Markman, 2017). We asked 400 participants to estimate the probability of different future events related to climate change. Our findings indicate that people hold coherent theories of climate change, that these theories were predictive of policy positions, and that they varied across individuals and across partisan groups. In particular, political independents and Republicans’s causal models underestimated the impacts of climate change. We also examined an educational intervention that explains a key mechanism of climate change (Ranney & Clark, 2016). Unfortunately, while the intervention increased mechanistic knowledge, it did not affect participants’ beliefs about climate outcomes. Nevertheless, the coherence of participants’ intuitive theories gives hope that other educational interventions could have meaningful and systematic effects on policy attitudes and political behaviors.

Understanding intuitive theories of climate change

Enabling efficient communication in artificial agents brings
us closer to machines that can cooperate with each other and
with human partners. Hand-engineered approaches have substantial limitations, leading to increased interest in methods for communication to emerge autonomously between artificial agents. Most of the research in the field explores unsituated communication in one-step referential tasks. The tasks are not temporally interactive and lack time pressures typically present in natural communication and language learning. In
these settings, agents can successfully learn what to communicate but not when or whether to communicate. Here, we extend the literature by assessing emergence of communication between reinforcement learning agents in a temporally interactive, cooperative task of navigating a gridworld environment. We show that, through multi-step interactions, agents develop just-in-time messaging protocols that enable them to
successfully solve the task. With memory—which provides
flexibility around message timing—agent pairs converge to a
look-ahead communication protocol, finding an optimal solution to the task more quickly than without memory. Lastly, we explore situated communication, enabling the acting agent to choose when and whether to communicate. With the opportunity cost of forgoing an action to communicate, the acting agent learns to solicit information sparingly, in line with the Gricean Maxim of quantity. Our results point towards the
importance of studying language emergence through situated
communication in multi-step interactions.

Towards Situated Communication in Multi-Step Interactions: Time is a Key Pressure in Communication Emergence

From classrooms to dinner parties, many of our everyday conversations take place in larger groups where speakers address multiple listeners at once. Such multiparty settings raise a number of challenges for classical theories of communication, which largely focus on dyadic interactions. In this study, we investigated how speakers adapt their referring expressions over time as a function of the feedback they receive from multiple parties. We collected a large corpus of multiparty repeated reference games (98 games, 390 participants, 116K words) where speakers designed referring expressions for groups of 1 to 5 listeners. Larger groups tended to use more words total and to introduce more new words; nonetheless, most groups were able to converge to more efficient conventions regardless of the number of listeners.

Two's company but six is a crowd: emergence of conventions in multiparty communication games

Language is a unique hallmark of humans, it is both learned and symbolic, which poses the problem of emergence: if neither form nor meaning is known, how can individuals communicate in the first place? The current study replicates work that investigates the emergence of signal forms and meanings and explores how Personal Need for Structure (PNS) of interacting partners can aid or hinder the emergence of communicative systems. We include an existing measure of personal need for structure to investigate its relationship with the emergence of such systems while participants play the embodied communication game (ECG). Similar to the original study, our work shows that a bootstrapping process and sufficient common ground are integral to the recognition of signalhood. Moreover, this process appears to be more successful for individuals who respond differently to a lack of structure as compared to their interaction partner. Contrary to what is usually assumed, our results indicate that not only shared expectations and biases seem to matter in communicative tasks, but that diversity in biases of communication partners can also be beneficial for the emergence of new communication systems.

Need for Structure and the Emergence of Communication

The literature suggests several hypotheses explaining adaptive vs. maladaptive character of task unrelated thoughts (TUT). However, it is still not clear what particular features can differentiate adaptive TUT from its maladaptive form. The main aim of the present study was to test the content and the context regulation hypothesis using daily sampling, that is to verify how TUT and task features are linked to momentary mood. 214 participants assessed their trait TUT through self-reported questionnaires and underwent a 7-day ecological momentary assessment of mood, TUT, and task characteristics measured 7 times by day. The results suggest that TUT particular features (i.e. lack of control, delay from the present moment, valence) are linked to both, lower mood valence and higher anxiety. Moreover control over the thoughts moderates the link between task characteristic (effort required by the task) and participants’ mood. Thus, from the clinical perspective, it seems more justified to take into account the particular TUT features instead of distinguishing specific TUT type (e.g. mind-wandering or rumination).

Task Unrelated Thoughts (TUT) affecting mood in ecological settings: from adaptive mind-wandering to maladaptive rumination.

Why does the mind wander? Recent theoretical models suggest mental content depends on a calculation that measures the expected rewards gained from the current task compared to other cognitive tasks and procedures. In Focused Attention Meditation (FA), participants practice attentional control by maintaining attention to an internal stimulus. Throughout the task, attentional lapses occur, in which there is an abrupt shift to mind wandering. We propose a model that formalizes attentional lapses as the interaction between a controller that boosts attentional resources to a target according to expected value calculations and a metacognitive monitoring procedure that stochastically observes internal contents. The model is applied to explain individual variation in button press data on an FA meditation task.

A Computational Model of Unintentional Mind Wandering in Focused Attention Meditation

We introduce a new empirical paradigm for studying naturalistic active learning, as well as new computational tools for jointly modeling algorithmic and rational theories of information search. Subjects in our task can ask questions and learn about hundreds of everyday items, but must retrieve queried items from memory. In order to maximize information gain, subjects need to retrieve sequences of dissimilar items. We find that subjects are not able to do this. Instead, associative memory mechanisms lead to the successive retrieval of similar items, an established memory effect known as semantic congruence. The extent of semantic congruence (and thus suboptimality) is unaffected by task instructions and incentives, though subjects are able to identify efficient query sequences when given a choice. Overall, our results indicate that subjects can distinguish between optimal and suboptimal search if explicitly asked to do so, but have difficulty implementing optimal search from memory. We conclude that associative memory processes place critical restrictions on people’s ability to ask good questions in naturalistic active learning tasks.

Limitations to Optimal Search in Naturalistic Active Learning

Accounts of human and machine concept learning face a fundamental challenge. Some approaches, notably deep learning, frequently achieve human-level performance on specific tasks but lack consistently human-like—i.e. generalizable, composable, and explainable—solutions. Others, including classic symbolic accounts, produce human-like hypotheses but scale poorly. We present a model of learning which is both human-level and human-like. It represents concepts as program-like expressions formed by applying a series of higher-order inferences that iteratively revise preexisting concepts into novel target concepts. Learning seeks the best combination of revisions under a Bayesian score. This model predicts learning behavior in 392 humans over 100 computationally sophisticated concepts more accurately than alternative models (Enumerate, Metagol, RobustFill, Fleet) while using three orders of magnitude less computation. This work shows how humans plausibly construct sophisticated algorithmic representations, a necessity for compelling human-like artificial intelligence.

Learning as Programming: Modeling Efficient Search in Human Concept Learning

Communication involves searching for optimal utterances
within memory and then evaluating those utterances against a
target goal. This task is substantially harder when informa-
tion about multiple concepts has to be communicated, such
as describing how music and tides are similar. Whether the
search process for this challenging communicative task con-
verges onto the optimal response relatively quickly, or involves
more strategic decision-making to evaluate different candi-
dates remains understudied. In this work, speakers gener-
ated single word “clues” that would enable a listener to cor-
rectly identify a pair of words among several distractor words.
Speakers and listeners generated candidates before producing
final responses. Each player was biased towards the first can-
didate(s) they generated, even when this candidate was sub-
optimal compared to other candidates, as was the case for less
related concepts. Furthermore, straying away from the initial
semantic “patch” of responses decreased accuracy in the game.
Overall, these findings suggest that individuals tend to identify
the relevant semantic cluster early on during semantic search,
and are likely to employ the “take-the-first” strategy for select-
ing utterances in ambiguous, ill-defined semantic contexts.

Premium content

Downloads

Next from CogSci 2022

I Know Your Next Move: Action Decisions in Dyadic Pick and Place Tasks

Similar lecture

Dropout Prompt Learning: Towards Robust and Adaptive Vision-Language Models