Related papers: Active Inference as a Model of Agency

The study of exploration in the domain of decision making has a long history but remains actively debated. From the vast literature that addressed this topic for decades under various points of view (e.g., developmental psychology,…

Active inference is a first principles approach for understanding the brain in particular, and sentient agents in general, with the single imperative of minimizing free energy. As such, it provides a computational account for modelling…

The aim of my Ph.D. thesis concerns Reasoning in Highly Reactive Environments. As reasoning in highly reactive environments, we identify the setting in which a knowledge-based agent, with given goals, is deployed in an environment subject…

We present a categorical formulation of the cognitive frameworks of Predictive Processing and Active Inference, expressed in terms of string diagrams interpreted in a monoidal category with copying and discarding. This includes diagrammatic…

Dynamic game theory is an increasingly popular tool for modeling multi-agent, e.g. human-robot, interactions. Game-theoretic models presume that each agent wishes to minimize a private cost function that depends on others' actions. These…

The integration of artificial intelligence (AI) into economic systems represents a transformative shift in decision-making frameworks, introducing novel dynamics between human and AI agents. This paper proposes a welfare model that…

Autonomous artificial agents must be able to learn behaviors in complex environments without humans to design tasks and rewards. Designing these functions for each environment is not feasible, thus, motivating the development of intrinsic…

Infants often exhibit goal-directed behaviors, such as reaching for a sensory stimulus, even when no external reward criterion is provided. These intrinsically motivated behaviors facilitate spontaneous exploration and learning of the body…

We discuss the possibility of world models and active exploration as emergent properties of open-ended behavior optimization in autonomous agents. In discussing the source of the open-endedness of living things, we start from the…

As the complexity of AI systems and their interactions with the world increases, generating explanations for their behaviour is important for safely deploying AI. For agents, the most natural abstractions for predicting behaviour attribute…

Infants are experts at playing, with an amazing ability to generate novel structured behaviors in unstructured environments that lack clear extrinsic reward signals. We seek to mathematically formalize these abilities using a neural network…

Active perception approaches select future viewpoints by using some estimate of the information gain. An inaccurate estimate can be detrimental in critical situations, e.g., locating a person in distress. However the true information gained…

Recent advancements in agentic test-time scaling allow models to gather environmental feedback before committing to final actions. A key limitation of existing methods is that they typically employ undifferentiated exploration strategies,…

Human agents routinely reason on instances with incomplete and muddied data (and weigh the cost of obtaining further features). In contrast, much of ML is devoted to the unrealistic, sterile environment where all features are observed and…

The enactive approach to cognition is typically proposed as a viable alternative to traditional cognitive science. Enactive cognition displaces the explanatory focus from the internal representations of the agent to the direct sensorimotor…

In this paper, we advocate for incorporating enactive approaches to perception and cognition into artificial intelligence (AI). Enactive approaches view perception as an active, skillful engagement with the world, where agents perceive by…

We revisit the role of instrumental value as a driver of adaptive behavior. In active inference, instrumental or extrinsic value is quantified by the information-theoretic surprisal of a set of observations measuring the extent to which…

Integrating theoretical neuroscience, decision theory, and probabilistic inference offers a promising route to understanding human cognition, yet concrete methodological bridges between agentic AI models and behavioral data analysis remain…

Theory of Mind (ToM) -- the ability to understand that others can have differing knowledge and goals -- enables agents to reason about others' beliefs while planning their own actions. We present a novel approach to multi-agent cooperation…

Inferential decision-making algorithms typically assume that an underlying probabilistic model of decision alternatives and outcomes may be learned a priori or online. Furthermore, when applied to robots in real-world settings they often…