Related papers: An Information Theoretic Representation of Agent D…
We argue that accountability mechanisms are needed in human-AI agent relationships to ensure alignment with user and societal interests. We propose a framework according to which AI agents' engagement is conditional on appropriate user…
Understanding realistic complex systems requires confronting significant conceptual, theoretical and experimental limitations rooted in the persistence of views that originated in the mechanics of simple moving bodies. We define the…
Predicting the outcomes of cyber-physical systems with multiple human interactions is a challenging problem. This article reviews a game theoretical approach to address this issue, where reinforcement learning is employed to predict the…
Continual learning is often motivated by the idea, known as the big world hypothesis, that "the world is bigger" than the agent. Recent problem formulations capture this idea by explicitly constraining an agent relative to the environment.…
We take the position that agent security must be approached as a systems problem: the AI model powering the agent must be treated as an untrusted component, and security invariants must be enforced at the system level. Through this lens,…
Modeling the interaction between traffic agents is a key issue in designing safe and non-conservative maneuvers in autonomous driving. This problem can be challenging when multi-modality and behavioral uncertainties are engaged. Existing…
In various economic environments, people observe other people with whom they strategically interact. We can model such information-sharing relations as an information network, and the strategic interactions as a game on the network. When…
Consider the process of collective decision-making, in which a group of individuals interactively select a preferred outcome from among a universe of alternatives. In this context, "representation" is the activity of making an individual's…
We consider the problem of controlling the group behavior of a large number of dynamic systems that are constantly interacting with each other. These systems are assumed to have identical dynamics (e.g., birds flock, robot swarm) and their…
We present our preliminary work on a multi-agent system involving the complex human phenomena of identity and dynamic teams. We outline our ongoing experimentation into understanding how these factors can eliminate some of the naive…
In large-scale multi-agent systems, the large number of agents and complex game relationship cause great difficulty for policy learning. Therefore, simplifying the learning process is an important research issue. In many multi-agent…
Agents are a special kind of AI-based software in that they interact in complex environments and have increased potential for emergent behaviour. Explaining such emergent behaviour is key to deploying trustworthy AI, but the increasing…
Existing approaches for generating human-aware agent behaviors have considered different measures of interpretability in isolation. Further, these measures have been studied under differing assumptions, thus precluding the possibility of…
According to Dennett, the same system may be described using a `physical' (mechanical) explanatory stance, or using an `intentional' (belief- and goal-based) explanatory stance. Humans tend to find the physical stance more helpful for…
An unaddressed challenge in multi-agent coordination is to enable AI agents to exploit the semantic relationships between the features of actions and the features of observations. Humans take advantage of these relationships in highly…
In Machine Learning and Robotics, the semantic content of visual features is usually provided to the system by a human who interprets its content. On the contrary, strictly unsupervised approaches have difficulties relating the statistics…
We introduce an agent-based model of interaction, drawing on the contingency approach from Luhmann's theory of social systems. The agent interactions are defined by the exchange of distinct messages. Message selection is based on the…
Recent advancements in the field of AI agents have impacted the way we work, enabling greater automation and collaboration between humans and agents. In the data visualization field, multi-agent systems can be useful for employing agents…
The availability of interaction devices has raised interest in techniques to support the user interface (UI). A UI specification describes the functions that a system provides to its users by capturing the interface details and includes…
Modern AI systems are complex workflows containing multiple components and data sources. Data provenance provides the ability to interrogate and potentially explain the outputs of these systems. However, provenance is often too detailed and…