English
Related papers

Related papers: Measuring Goal-Directedness

200 papers

In practical electrocardiography (ECG) interpretation, the scarcity of well-annotated data is a common challenge. Transfer learning techniques are valuable in such situations, yet the assessment of transferability has received limited…

Signal Processing · Electrical Eng. & Systems 2024-06-13 Cuong V. Nguyen , Hieu Minh Duong , Cuong D. Do

Efficient approximation lies at the heart of large-scale machine learning problems. In this paper, we propose a novel, robust maximum entropy algorithm, which is capable of dealing with hundreds of moments and allows for computationally…

Machine Learning · Statistics 2019-06-05 Diego Granziol , Binxin Ru , Stefan Zohren , Xiaowen Doing , Michael Osborne , Stephen Roberts

Safe generalization in reinforcement learning requires not only that a learned policy acts capably in new situations, but also that it uses its capabilities towards the pursuit of the designer's intended goal. The latter requirement may…

Currently, the world experiences an unprecedentedly increasing generation of application data, from sensor measurements to video streams, thanks to the extreme connectivity capability provided by 5G networks. Going beyond 5G technology,…

Signal Processing · Electrical Eng. & Systems 2022-04-21 Mattia Merluzzi , Miltiadis C. Filippou , Leonardo Gomes Baltar , Emilio Calvanese Strinati

Despite recent advances, goal-directed generation of structured discrete data remains challenging. For problems such as program synthesis (generating source code) and materials design (generating molecules), finding examples which satisfy…

Machine Learning · Computer Science 2020-10-26 Amina Mollaysa , Brooks Paige , Alexandros Kalousis

The field of AI alignment is concerned with AI systems that pursue unintended goals. One commonly studied mechanism by which an unintended goal might arise is specification gaming, in which the designer-provided specification is flawed in a…

Machine Learning · Computer Science 2022-11-03 Rohin Shah , Vikrant Varma , Ramana Kumar , Mary Phuong , Victoria Krakovna , Jonathan Uesato , Zac Kenton

In long-horizon tasks, recent agents based on Large Language Models (LLMs) face a significant challenge that sparse, outcome-based rewards make it difficult to assign credit to intermediate steps. Previous methods mainly focus on creating…

Machine Learning · Computer Science 2025-09-12 Jiawei Wang , Jiacai Liu , Yuqian Fu , Yingru Li , Xintao Wang , Yuan Lin , Yu Yue , Lin Zhang , Yang Wang , Ke Wang

Causal inference is crucial for humans to explore the world, which can be modeled to enable an agent to efficiently explore the environment in reinforcement learning. Existing research indicates that establishing the causality between…

Machine Learning · Computer Science 2025-08-14 Yan Yu , Yaodong Yang , Zhengbo Lu , Chengdong Ma , Wengang Zhou , Houqiang Li

Obtaining high-quality labels is costly, whereas unlabeled covariates are often abundant, motivating semi-supervised inference methods with reliable uncertainty quantification. Prediction-powered inference (PPI) leverages a machine-learning…

Machine Learning · Statistics 2026-05-29 Se Yoon Lee , Jae Kwang Kim

Entropy Search (ES) and Predictive Entropy Search (PES) are popular and empirically successful Bayesian Optimization techniques. Both rely on a compelling information-theoretic motivation, and maximize the information gained about the…

Machine Learning · Statistics 2018-08-06 Zi Wang , Stefanie Jegelka

Multi-agent credit assignment is a fundamental challenge for cooperative multi-agent reinforcement learning (MARL), where a team of agents learn from shared reward signals. The Individual-Global-Max (IGM) condition is a widely used…

Machine Learning · Computer Science 2026-02-04 Wen-Tse Chen , Yuxuan Li , Shiyu Huang , Jiayu Chen , Jeff Schneider

Dropped into an unknown environment, what should an agent do to quickly learn about the environment and how to accomplish diverse tasks within it? We address this question within the goal-conditioned reinforcement learning paradigm, by…

Machine Learning · Computer Science 2023-03-24 Edward S. Hu , Richard Chang , Oleh Rybkin , Dinesh Jayaraman

MEG and EEG are noninvasive functional neuroimaging techniques that provide recordings of brain activity with high temporal resolution, and thus provide a unique window to study fast time-scale neural dynamics in humans. However, the…

Applications · Statistics 2015-11-13 Camilo Lamus , Matti S. Hamalainen , Emery N. Brown , Patrick L. Purdon

Ergodic optimization aims to single out dynamically invariant Borel probability measures which maximize the integral of a given "performance" function. For a continuous self-map of a compact metric space and a dense set of continuous…

Dynamical Systems · Mathematics 2017-04-20 Mao Shinoda

Optimizing a given metric is a central aspect of most current AI approaches, yet overemphasizing metrics leads to manipulation, gaming, a myopic focus on short-term goals, and other unexpected negative consequences. This poses a fundamental…

Computers and Society · Computer Science 2020-02-21 Rachel Thomas , David Uminsky

This paper presents a novel framework for goal-oriented optimal static sensor placement and dynamic sensor steering in PDE-constrained inverse problems, utilizing a Bayesian approach accelerated by low-rank approximations. The framework is…

Numerical Analysis · Mathematics 2025-07-09 Marco Mattuschka , Noah An der Lan , Max von Danwitz , Daniel Wolff , Alexander Popp

How do cognitive agents decide what is the relevant information to learn and how goals are selected to gain this knowledge? Cognitive agents need to be motivated to perform any action. We discuss that emotions arise when differences between…

Robotics · Computer Science 2020-07-30 Guido Schillaci , Alejandra Ciria , Bruno Lara

A new class of models for dynamic networks is proposed, called mutually exciting point process graphs (MEG). MEG is a scalable network-wide statistical model for point processes with dyadic marks, which can be used for anomaly detection…

Social and Information Networks · Computer Science 2023-10-25 Francesco Sanna Passino , Nicholas A. Heard

Maximum Causal Entropy (MCE) Inverse Optimal Control (IOC) has become an effective tool for modelling human behaviour in many control tasks. Its advantage over classic techniques for estimating human policies is the transferability of the…

Systems and Control · Computer Science 2016-07-20 Felix Schmitt , Hans-Joachim Bieg , Dietrich Manstetten , Michael Herman , Rainer Stiefelhagen

Optimal experimental design (OED) plays an important role in the problem of identifying uncertainty with limited experimental data. In many applications, we seek to minimize the uncertainty of a predicted quantity of interest (QoI) based on…

Optimization and Control · Mathematics 2022-01-06 Keyi Wu , Peng Chen , Omar Ghattas