English
Related papers

Related papers: Information theoretic approach to interactive lear…

200 papers

Systems of interacting particles or agents have wide applications in many disciplines such as Physics, Chemistry, Biology and Economics. These systems are governed by interaction laws, which are often unknown: estimating them from…

Machine Learning · Statistics 2020-07-16 Fei Lu , Mauro Maggioni , Sui Tang

Active Inference is a closed-loop computational theoretical basis for understanding behaviour, based on agents with internal probabilistic generative models that encode their beliefs about how hidden states in their environment cause their…

Human-Computer Interaction · Computer Science 2024-12-20 Roderick Murray-Smith , John H. Williamson , Sebastian Stein

Information theory gives rise to a novel method for causal skeleton discovery by expressing associations between variables as tensors. This tensor-based approach reduces the dimensionality of the data needed to test for conditional…

Machine Learning · Statistics 2020-11-10 David Sigtermans

We investigate a toy model of inductive interacting agents aiming to forecast a continuous, exogenous random variable E. Private information on E is spread heterogeneously across agents. Herding turns out to be the preferred forecasting…

Physics and Society · Physics 2015-05-13 S. Gualdi , A. De Martino

Information theory and the framework of information dynamics have been used to provide tools to characterise complex systems. In particular, we are interested in quantifying information storage, information modification and information…

Information Theory · Computer Science 2013-03-25 Oliver Obst , Joschka Boedecker , Benedikt Schmidt , Minoru Asada

In this article, we propose a sampling-based motion planning algorithm equipped with an information-theoretic convergence criterion for incremental informative motion planning. The proposed approach allows dense map representations and…

Robotics · Computer Science 2019-05-24 Maani Ghaffari Jadidi , Jaime Valls Miro , Gamini Dissanayake

Intrinsically motivated reinforcement learning aims to address the exploration challenge for sparse-reward tasks. However, the study of exploration methods in transition-dependent multi-agent settings is largely absent from the literature.…

Machine Learning · Computer Science 2019-12-30 Tonghan Wang , Jianhao Wang , Yi Wu , Chongjie Zhang

We introduce an information-theoretic framework that views learning as universal prediction under log loss, characterized through regret bounds. Central to the framework is an effective notion of architecture-based model complexity, defined…

Machine Learning · Computer Science 2025-11-04 Meir Feder , Ruediger Urbanke , Yaniv Fogel

Scenarios requiring humans to choose from multiple seemingly optimal actions are commonplace, however standard imitation learning often fails to capture this behavior. Instead, an over-reliance on replicating expert actions induces…

Robotics · Computer Science 2022-11-08 Hanbit Oh , Hikaru Sasaki , Brendan Michael , Takamitsu Matsubara

Bounded agents are limited by intrinsic constraints on their ability to process information that is available in their sensors and memory and choose actions and memory updates. In this dissertation, we model these constraints as…

Machine Learning · Computer Science 2017-03-31 Roy Fox

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…

Neurons and Cognition · Quantitative Biology 2020-10-14 Alvaro Ovalle , Simon M. Lucas

In this position paper, I first describe a new perspective on machine learning (ML) by four basic problems (or levels), namely, "What to learn?", "How to learn?", "What to evaluate?", and "What to adjust?". The paper stresses more on the…

Information Theory · Computer Science 2015-01-20 Bao-Gang Hu

Deep learning has revolutionized many areas of machine learning, from computer vision to natural language processing, but these high-performance models are generally "black box." Explaining such models would improve transparency and trust…

Machine Learning · Computer Science 2023-05-18 Daniel Lundstrom , Meisam Razaviyayn

Interactive reinforcement learning has become an important apprenticeship approach to speed up convergence in classic reinforcement learning problems. In this regard, a variant of interactive reinforcement learning is policy shaping which…

Artificial Intelligence · Computer Science 2019-04-16 Francisco Cruz , Sven Magg , Yukie Nagai , Stefan Wermter

It has been postulated that a good representation is one that disentangles the underlying explanatory factors of variation. However, it remains an open question what kind of training framework could potentially achieve that. Whereas most…

Optimal control of complex environments with robotic systems faces two complementary and intertwined challenges: efficient organization of sensory state information and far-sighted action planning. Because the reinforcement learning…

Machine Learning · Computer Science 2026-01-30 Abdullah Akgül , Gulcin Baykal , Manuel Haußmann , Mustafa Mert Çelikok , Melih Kandemir

Learning-based control has attracted significant attention in recent years, especially for plants that are difficult to model based on first-principles. A key issue in learning-based control is how to make efficient use of data as the…

Systems and Control · Electrical Eng. & Systems 2025-08-05 Kaikai Zheng , Dawei Shi , Sandra Hirche , Yang Shi

A mathematical model for behavioral changes by pair interactions (i.e. due to direct contact) of individuals is developed. Three kinds of pair interactions can be distinguished: Imitative processes, avoidance processes, and compromising…

Statistical Mechanics · Physics 2007-05-23 Dirk Helbing

We propose a data-driven framework to enable the modeling and optimization of human-machine interaction processes, e.g., systems aimed at assisting humans in decision-making or learning, work-load allocation, and interactive advertising.…

Machine Learning · Computer Science 2019-03-19 Jiaxiao Zheng , Gustavo de Veciana

We propose a new online learning model for learning with preference feedback. The model is especially suited for applications like web search and recommender systems, where preference data is readily available from implicit user feedback…

Machine Learning · Computer Science 2011-11-04 Pannagadatta K. Shivaswamy , Thorsten Joachims