English
Related papers

Related papers: General Agents Contain World Models, even under Pa…

200 papers

In this paper we introduce a general estimation methodology for learning a model of human perception and control in a sensorimotor control task based upon a finite set of demonstrations. The model's structure consists of i the agent's…

Machine Learning · Computer Science 2025-05-02 Ran Wei , Anthony D. McDonald , Alfredo Garcia , Gustav Markkula , Johan Engstrom , Matthew O'Kelly

This brief note considers the problem of learning with dynamic-optimizing principal-agent setting, in which the agents are allowed to have global perspectives about the learning process, i.e., the ability to view things according to their…

Machine Learning · Statistics 2026-01-12 Getachew K. Befekadu

Agents can achieve effective interaction with previously unknown other agents by maintaining beliefs over a set of hypothetical behaviours, or types, that these agents may have. A current limitation in this method is that it does not…

Multiagent Systems · Computer Science 2019-06-27 Stefano V. Albrecht , Peter Stone

In this paper we provide a broad framework for describing learning agents in general quantum environments. We analyze the types of classically specified environments which allow for quantum enhancements in learning, by contrasting…

Quantum Physics · Physics 2015-07-31 Vedran Dunjko , Jacob M. Taylor , Hans J. Briegel

The "small agent, big world" frame offers a conceptual view that motivates the need for continual learning. The idea is that a small agent operating in a much bigger world cannot store all information that the world has to offer. To perform…

Machine Learning · Computer Science 2024-08-07 Saurabh Kumar , Hong Jun Jeon , Alex Lewandowski , Benjamin Van Roy

In model-based reinforcement learning, generative and temporal models of environments can be leveraged to boost agent performance, either by tuning the agent's representations during training or via use as part of an explicit planning…

In order to meet the diverse challenges in solving many real-world problems, an intelligent agent has to be able to dynamically construct a model of its environment. Objects facilitate the modular reuse of prior knowledge and the…

Machine Learning · Computer Science 2019-06-05 Sjoerd van Steenkiste , Klaus Greff , Jürgen Schmidhuber

Giving autonomous agents the ability to forecast their own outcomes and uncertainty will allow them to communicate their competencies and be used more safely. We accomplish this by using a learned world model of the agent system to forecast…

Machine Learning · Computer Science 2023-02-20 Aastha Acharya , Rebecca Russell , Nisar R. Ahmed

The tasks that an agent will need to solve often are not known during training. However, if the agent knows which properties of the environment are important then, after learning how its actions affect those properties, it may be able to…

Artificial Intelligence · Computer Science 2019-04-29 Amy Zhang , Adam Lerer , Sainbayar Sukhbaatar , Rob Fergus , Arthur Szlam

Social dilemmas are situations where groups of individuals can benefit from mutual cooperation but conflicting interests impede them from doing so. This type of situations resembles many of humanity's most critical challenges, and…

Machine Learning · Computer Science 2023-05-22 Manuel Rios , Nicanor Quijano , Luis Felipe Giraldo

In a classic paper, Conant and Ashby claimed that "every good regulator of a system must be a model of that system." Artificial Life has produced many examples of systems that perform tasks with apparently no model in sight; these suggest…

Artificial Intelligence · Computer Science 2025-08-22 Nathaniel Virgo , Martin Biehl , Manuel Baltieri , Matteo Capucci

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…

Machine Learning · Computer Science 2018-11-01 Nick Haber , Damian Mrowca , Li Fei-Fei , Daniel L. K. Yamins

We develop a general problem setting for training and testing the ability of agents to gather information efficiently. Specifically, we present a collection of tasks in which success requires searching through a partially-observed…

Machine Learning · Computer Science 2016-12-09 Philip Bachman , Alessandro Sordoni , Adam Trischler

Real-world generalization, e.g., deciding to approach a never-seen-before animal, relies on contextual information as well as previous experiences. Such a seemingly easy behavioral choice requires the interplay of multiple neural…

Neurons and Cognition · Quantitative Biology 2022-01-17 Peer Herholz , Eddy Fortier , Mariya Toneva , Nicolas Farrugia , Leila Wehbe , Valentina Borghesani

In several domains such as linguistics, molecular biology or social sciences, holistic effects are hardly well-defined by modeling with single units, but more and more studies tend to understand macro structures with the help of meaningful…

Computation and Language · Computer Science 2016-06-02 Nicolas Turenne

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.…

Artificial Intelligence · Computer Science 2025-12-30 Alex Lewandowski , Adtiya A. Ramesh , Edan Meyer , Dale Schuurmans , Marlos C. Machado

Agents trained by reinforcement learning (RL) often fail to generalize beyond the environment they were trained in, even when presented with new scenarios that seem similar to the training environment. We study the query complexity required…

Machine Learning · Computer Science 2021-10-27 Dhruv Malik , Yuanzhi Li , Pradeep Ravikumar

The hidden-action model captures a fundamental problem of principal-agent theory and provides an optimal sharing rule when only the outcome but not the effort can be observed. However, the hidden-action model builds on various explicit and…

General Economics · Economics 2020-04-15 Stephan Leitner , Friederike Wall

Human beings do not observe the world from the outside, but rather are fully embedded in it. The sciences, however, often give the observer both a "god's eye" perspective and substantial a~priori knowledge. Motivated by W. Ross Ashby's…

Quantum Physics · Physics 2016-11-11 Chris Fields

We consider an unsupervised classifying agent that evolves by enforcing self-consistency of its labels under continual exposure to a data-generating environment. Because the agent's predictions feed back into its own regularized updates,…

Disordered Systems and Neural Networks · Physics 2025-09-30 Sebastiano Ariosto , Jerome Garnier-Brun , Luca Saglietti , Davide Straziota