Related papers: From Curiosity to Competence: How World Models Int…

Efficient exploration is a long-standing problem in sensorimotor learning. Major advances have been demonstrated in noise-free, non-stochastic domains such as video games and simulation. However, most of these formulations either get stuck…

This chapter examines the relationship between curiosity and metacognition as critical drivers of autonomous and self-regulated learning. We synthesize recent research to propose a unified framework integrating behavioral, computational,…

Opponent modeling consists in modeling the strategy or preferences of an agent thanks to the data it provides. In the context of automated negotiation and with machine learning, it can result in an advantage so overwhelming that it may…

The relation between self awareness and intelligence is an open problem these days. Despite the fact that self awarness is usually related to Emotional Intelligence, this is not the case here. The problem described in this paper is how to…

Reinforcement Learning has emerged as a strong alternative to solve optimization tasks efficiently. The use of these algorithms highly depends on the feedback signals provided by the environment in charge of informing about how good (or…

Competition for a limited resource is the hallmark of many complex systems, and often, that resource turns out to be the physical space itself. In this work, we study a novel model designed to elucidate the dynamics and emergence in complex…

Curiosity for machine agents has been a focus of intense research. The study of human and animal curiosity, particularly specific curiosity, has unearthed several properties that would offer important benefits for machine learners, but that…

Biological infants are naturally curious and try to comprehend their physical surroundings by interacting, in myriad multisensory ways, with different objects - primarily macroscopic solid objects - around them. Through their various…

A default assumption in the design of reinforcement-learning algorithms is that a decision-making agent always explores to learn optimal behavior. In sufficiently complex environments that approach the vastness and scale of the real world,…

Model-based Reinforcement Learning approaches have the promise of being sample efficient. Much of the progress in learning dynamics models in RL has been made by learning models via supervised learning. But traditional model-based…

Learning in environments with sparse rewards remains a fundamental challenge in reinforcement learning. Artificial curiosity addresses this limitation through intrinsic rewards to guide exploration, however, the precise formulation of these…

In Reinforcement Learning (RL), an agent explores the environment and collects trajectories into the memory buffer for later learning. However, the collected trajectories can easily be imbalanced with respect to the achieved goal states.…

To quickly solve new tasks in complex environments, intelligent agents need to build up reusable knowledge. For example, a learned world model captures knowledge about the environment that applies to new tasks. Similarly, skills capture…

World models improve a learning agent's ability to efficiently operate in interactive and situated environments. This work focuses on the task of building world models of text-based game environments. Text-based games, or interactive…

A long-term goal of language agents is to learn and improve through their own experience, ultimately outperforming humans in complex, real-world tasks. However, training agents from experience data with reinforcement learning remains…

We present ScienceWorld, a benchmark to test agents' scientific reasoning abilities in a new interactive text environment at the level of a standard elementary school science curriculum. Despite the transformer-based progress seen in…

World models are emerging as a transformative paradigm in artificial intelligence, enabling agents to construct internal representations of their environments for predictive reasoning, planning, and decision-making. By learning latent…

Evaluating the general abilities of intelligent agents requires complex simulation environments. Existing benchmarks typically evaluate only one narrow task per environment, requiring researchers to perform expensive training runs on many…

Spatial reasoning in partially observable environments has often been approached through passive predictive models, yet theories of embodied cognition suggest that genuinely useful representations arise only when perception is tightly…

Curiosity serves as a pivotal conduit for human beings to discover and learn new knowledge. Recent advancements of large language models (LLMs) in natural language processing have sparked discussions regarding whether these models possess…