Related papers: Tracking Emotions: Intrinsic Motivation Grounded o…
In dynamic settings each economic agent's choices can be revealing of her private information. This elicitation via the rationalization of observable behavior depends each agent's perception of which payoff-relevant contingencies other…
Goal-models (GM) have been used in adaptive systems engineering for their ability to capture the different ways to fulfill the requirements. Contextual GM (CGM) extend these models with the notion of context and context-dependent…
Humans effortlessly "program" one another by communicating goals and desires in natural language. In contrast, humans program robotic behaviours by indicating desired object locations and poses to be achieved, by providing RGB images of…
Intrinsic Motivation (IM) aims to train agents without external rewards, enabling useful behavior to emerge from the agent's interaction with its environment alone. However, the dominant IM approaches rely on information-theoretic…
Background: Exploration of the physical environment is an indispensable precursor to information acquisition and knowledge consolidation for living organisms. Yet, current artificial intelligence models lack these autonomy capabilities…
This exercise proposes a learning mechanism to model economic agent's decision-making process using an actor-critic structure in the literature of artificial intelligence. It is motivated by the psychology literature of learning through…
In dynamic programming and reinforcement learning, the policy for the sequential decision making of an agent in a stochastic environment is usually determined by expressing the goal as a scalar reward function and seeking a policy that…
As AI closely interacts with human society, it is crucial to ensure that its behavior is safe, altruistic, and aligned with human ethical and moral values. However, existing research on embedding ethical considerations into AI remains…
We study opinion dynamics in a population of interacting adaptive agents voting on a set of complex multidimensional issues. We consider agents which can classify issues into for or against. The agents arrive at the opinions about each…
Learned dynamics models combined with both planning and policy learning algorithms have shown promise in enabling artificial agents to learn to perform many diverse tasks with limited supervision. However, one of the fundamental challenges…
Power-seeking behavior is a key source of risk from advanced AI, but our theoretical understanding of this phenomenon is relatively limited. Building on existing theoretical results demonstrating power-seeking incentives for most reward…
The objective of a reinforcement learning agent is to behave so as to maximise the sum of a suitable scalar function of state: the reward. These rewards are typically given and immutable. In this paper, we instead consider the proposition…
Prior efforts to create an autonomous computer system capable of predicting what a human being is thinking or feeling from facial expression data have been largely based on outdated, inaccurate models of how emotions work that rely on many…
Exploring rich environments and evaluating one's actions without prior knowledge is immensely challenging. In this paper, we propose Motif, a general method to interface such prior knowledge from a Large Language Model (LLM) with an agent.…
An efficient policy search algorithm should estimate the local gradient of the objective function, with respect to the policy parameters, from as few trials as possible. Whereas most policy search methods estimate this gradient by observing…
This paper presents a comprehensive overview of autotelic Reinforcement Learning (RL), emphasizing the role of intrinsic motivations in the open-ended formation of skill repertoires. We delineate the distinctions between knowledge-based and…
Training and education in human-centered fields require authentic practice, yet realistic simulations of human behavior have remained limited. We present a multi-agent psychological simulation system that models internal cognitive-affective…
In the same way that generative models today conduct most of their training in a self-supervised fashion, how can agentic models conduct their training in a self-supervised fashion, interactively exploring, learning, and preparing to…
Current theoretical and computational models of dopamine-based reinforcement learning are largely rooted in the classical behaviorist tradition, and envision the organism as a purely reactive recipient of rewards and punishments, with…
Managing health lays the core foundation to enabling quality life experiences. Modern computer science research, and especially the field of recommender systems, has enhanced the quality of experiences in fields such as entertainment,…