Canada

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.

CogSci 2022

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

AAMAS is the largest and most influential conference in the area of agents and multiagent systems, bringing together researchers and practitioners in all areas of agent technology and providing and internationally renowned high-profile forum for publishing and finding out about the latest developments in the field. AAMAS is the flagship conference of the non-profit International Foundation for Autonomous Agents and Multiagent Systems (IFAAMAS).  

![](https://assets.underline.io/uploads/markdown_image/1/image/ce4604bd54468a006164d16e080204fb.jpg)

Please click on the button below to register for this event.

If you are registered and see this page please check the account email you are logged in with. It must be the same as for the registration.

If you still have trouble accessing the contact please contact support at aamas2021@underline.io 

AAMAS 2021

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. 





When people think about the features of common objects, like scissors, they often spontaneously recall a central feature: scissors cut things. They tend not to recall other features of scissors, e.g., that they have handles. The present paper posits a novel explanation for the behavior: the features people recall first and most often reflect semantic generalizations of kinds. A recent taxonomy of such generalizations suggests that people represent privileged links between kinds and their features known as principled connections (Prasada et al., 2013). Several tests diagnose principled connections: for instance, principled connections reflect norms, so one way to diagnose the presence of a principled connection is to test the acceptability of sentences of the form all normal Xs have feature Y, as in all normal cars have four wheels. We tested whether participants accept generalizations about the normality of features produced in a semantic feature production task (Experiments 1 and 2) as well as self-referential generalizations (Experiment 3). The experiments provided participants with generalizations about features listed first and most often as well as features that people list less frequently. They found that people readily accepted generalizations that diagnose the presence of principled connections. The results corroborate the view that principled connections help people recall the features of conceptual categories.

Frequently produced semantic features reflect principled connections

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.

Fast and frugal memory search for communication

Competing perspectives on building ethical AI: psychological, philosophical, and computational approaches

Is the mind equipped with universal biases? If so, how can we account for the well-recognized diversity ofhuman cognition? And if universal biases do exist,what is their source—do theyreflect innate principles of core knowledge, or can they emerge from domain-general pressures? Finally, how can we, cognitive scientists, “get” human nature better—minimizing the pitfalls of our intuitive cognitive biases and our narrow WEIRD perspective?This symposium seeks to address the question of human nature from a broad interdisciplinary perspective. We begin by examining the notion of “human nature” and the concept of innateness (Samuels)and exploring some of the challenges facing its discovery by the confinements of our own human cognition (Berent). The next talk (Culbertson) exposesthe tensions between cognitive universals and diversity in the domain of language, contrasts domain-specific with domain-general explanations of these facts, and demonstratesthe merits of a cross-linguistic perspective. The last talk (Majid) considershow language is used to express perceptual categories across cultures, explores how culture and nurture can shed light on human nature, and highlightssome of the challenges in sifting through the tight nature-nurture interactions. Throughout these four talks, we hope to highlight both theoretical gains and limits in our current understanding of innateness anddomain-specificity, the value of exploring human diversity, and the challenges we, humans face when we seek to explore our own human nature.

Premium content

Downloads

Next from CogSci 2022

Frequently produced semantic features reflect principled connections

Similar lecture

Intrinsic Motivated Multi-Agent Communication