Information Gain

Follow this topic Ask about this topic

Latest papers

13 papers3 papers in the last four weeks, with none the four weeks before. 0.0% of all new papers.

What Information Buys in Active Inference
Oct 13, 2026Melih Kandemir, Mustafa Mert ÇelikokRL Exploration Active Inference
Department of Mathematics and Computer Science, University of Southern Denmark
AGILE-GS: Anchor-Guided Fast Next-Best-View Selection for Active 3D Gaussian Splatting
Sep 28, 2026Amirhossein Mollaei Khass, Nader Motee3D Gaussian Splatting Next-Best-View Planning
Department of Mechanical Engineering and Mechanics, Lehigh University, Bethlehem, PA, 18015, USA
LAVOIR: Teaching a Single-Pass Decision Encoder When and What to Ask with Amortized Value of Information
Sep 25, 2026Furkan Yilmaz, Habibe Aleyna Tasdemir, Muhammed Faruk GozayLLM Decision-Making Active Information Gathering
Ask to Be Sure: Informative Interactions for Confident Multi-Turn LLM Recommendation
Aug 16, 2026Cedar Site Bai, Zhenyu Liao, Duanshun Li +6Information Gain Recommender Systems
Amazon · Sunnyvale, CA, USA · Seattle, WA, USA +1
GO-PRE: Goal-Oriented Next-Best-View Selection via Predictive Rendering Entropy for Active 3D Reconstruction
Jul 31, 2026Yan Song, Zhihao Li, Chenglong Li +3Next-Best-View Planning 3D Reconstruction
College of Intelligent Robotics and Advanced Manufacturing, Fudan University, Shanghai, China · School of Software, Shandong University, Jinan, China · School of Data Science and Engineering, East China Normal University, Shanghai, China
Reinforcement Learning for Heterogeneous Sensor Selection in Maritime Surveillance
Jul 3, 2026Andrei Starodubov, Yaqub Aris Prabowo, Andreas Hadjipieris +2Maritime Surveillance Information Gain
Cyprus Marine and Maritime Institute, Larnaca, Cyprus · Technical University of Denmark, Lyngby, Denmark
Ask When It Pays: Cost-Aware Open-Ended Interaction for Instance Goal Navigation
Jun 2, 2026Xunyi Zhao, Sihao Lin, Gengze Zhou +5Embodied Navigation AI Agent Benchmarks
1Adelaide University · 2Responsible AI Research Centre, Australian Institute for Machine Learning · Institute for Infocomm Research (I2R), A*STAR +2
Uncertainty-Aware Clarification in LLM Agents with Information Gain
Jun 2, 2026Mengyi Deng, Zhiwei Li, Xin Li +4Clarification Question Generation Tool-Using Agents
Information Hub, HKUST(GZ) · Jilin University · et al.
CIG: Exploration via Conditional Information Gain
May 20, 2026Tim Joseph, Marcus Fechner, Philipp Stegmaier +2Intrinsic Reward Methods Intrinsic Motivation
FZI · KIT
Asymptotically-Bounded 3D Frontier Exploration enhanced with Bayesian Information Gain
Apr 3, 2026John Lewis, Meysam Basiri, Pedro U. LimaInformation Gain Frontier-Based Exploration
Institute for Systems and Robotics, Instituto Superior Técnico, Universidade de Lisboa, Lisbon 1049-001, Portugal
A Proper Scoring Rule for Virtual Staining
Feb 26, 2026Samuel Tonks, Steve Hood, Ryan Musso +5Information Gain Virtual Staining
School of Computer Science, University of Birmingham, Birmingham, UK · GSK Drug Metabolism & Pharmacokinetics, GSK Medicines Research Centre, Stevenage, UK · GSK Genome Biology, Collegeville, PA, USA +1
MedClarify: An information-seeking AI agent for medical diagnosis with case-specific follow-up questions
Feb 19, 2026Hui Min Wong, Philip Heesen, Pascal Janetzky +2Information Gain Medical LLMs
LMU Munich, Munich, Germany · Munich Center for Machine Learning, Germany · Department of Neuroradiology, Heidelberg University, Heidelberg, Germany
Large Language Model Selection with Limited Annotations
Oct 10, 2025Yavuz Durmazkeser, Patrik Okanovic, Andreas Kirsch +2Model Selection LLM Evaluation
TU Delft · ETH Zurich

Oct 13, 2026J/K move · Enter open · S save

What Information Buys in Active Inference

Melih Kandemir, Mustafa Mert Çelikok

Department of Mathematics and Computer Science, University of Southern Denmark

RL Exploration Active Inference Uncertainty-Aware Exploration Information Gain Regret Minimization in RL Bayesian RL

Open paper AskPDF arXiv

Information-theoretic exploration is of primary interest in methodological studies of reinforcement learning (RL) and computational cognitive neuroscience, while the established RL theory builds regret guarantees on confidence sets. This situation leaves open the conditions under which the information-driven exploration found in nature is more advantageous than the exploration of the established RL theory. We put the state-of-the-art methods of these two paradigms, Active Inference (AIF) and Bayes-UCBVI, on an equal footing: both act through the same state abstraction of a tabular MDP with

S

states, and their greedy forms differ only in the exploration term. We find that AIF's information gain decays too fast to serve as a confidence width, locking greedy agents that explore by it out of the optimal action. Calibrating the information gain by a square root yields calibrated AIF, which attains regret of order

\sqrt T

for an exact abstraction, but no better guarantee than Bayes-UCBVI for a fixed reward. When an adversary chooses rewards from the agent's data, Bayes-UCBVI's value-specific widths lock out, whereas calibrated AIF pays a factor

\sqrt S

, which no goal-memoryless agent avoids on some MDP whose start states the adversary also chooses. Calibrated information gain thus acts as a reward-agnostic

\ell_1

confidence set, preferable to value-specific widths when rewards are chosen from the agent's data, not when they are fixed.