4.6 Article

Quantifying Reinforcement-Learning Agent's Autonomy, Reliance on Memory and Internalisation of the Environment

相关参考文献

注意:仅列出部分参考文献,下载原文获取全部文献信息。
Article Multidisciplinary Sciences

Bits and pieces: understanding information decomposition from part-whole relationships and formal logic

A. J. Gutknecht et al.

Summary: Partial information decomposition (PID) aims to decompose multivariate mutual information into basic components called "information atoms", which can be derived from the relationships between information atoms and mutual information terms, as well as logical constraints describing how information atoms can be accessed.

PROCEEDINGS OF THE ROYAL SOCIETY A-MATHEMATICAL PHYSICAL AND ENGINEERING SCIENCES (2021)

Article Physics, Fluids & Plasmas

Introducing a differentiable measure of pointwise shared information

Abdullah Makkeh et al.

Summary: Partial information decomposition examines how a set of source variables conveys information about a target variable, with existing measures being non-differentiable. The paper introduces a differentiable measure based solely on information theory principles, emphasizing local learning and adhering to the target chain rule.

PHYSICAL REVIEW E (2021)

Article Physics, Multidisciplinary

A Path-Based Partial Information Decomposition

David Sigtermans

ENTROPY (2020)

Article Multidisciplinary Sciences

Grandmaster level in StarCraft II using multi-agent reinforcement learning

Oriol Vinyals et al.

NATURE (2019)

Article Computer Science, Artificial Intelligence

CASH only: Constitutive autonomy through motorsensory self-programming

Olivier L. Georgeon et al.

COGNITIVE SYSTEMS RESEARCH (2019)

Article Physics, Multidisciplinary

BROJA-2PID: A Robust Estimator for Bivariate Partial Information Decomposition

Abdullah Makkeh et al.

ENTROPY (2018)

Article Physics, Multidisciplinary

Analyzing Information Distribution in Complex Systems

Sten Sootla et al.

ENTROPY (2017)

Article Physics, Multidisciplinary

The Partial Information Decomposition of Generative Neural Network Models

Tycho M. S. Tax et al.

ENTROPY (2017)

Article Physics, Multidisciplinary

Bivariate Partial Information Decomposition: The Optimization Perspective

Abdullah Makkeh et al.

ENTROPY (2017)

Article Physics, Multidisciplinary

Quantifying Synergistic Information Using Intermediate Stochastic Variables

Rick Quax et al.

ENTROPY (2017)

Article Robotics

Hierarchical Quantification of Synergy in Channels

Paolo Perrone et al.

FRONTIERS IN ROBOTICS AND AI (2016)

Article Physics, Multidisciplinary

Quantifying Unique Information

Nils Bertschinger et al.

ENTROPY (2014)

Article Physics, Fluids & Plasmas

Bivariate measure of redundant information

Malte Harder et al.

PHYSICAL REVIEW E (2013)

Article Computer Science, Artificial Intelligence

Empowerment for continuous agent-environment systems

Tobias Jung et al.

ADAPTIVE BEHAVIOR (2011)

Article Computer Science, Artificial Intelligence

Measuring Autonomy and Emergence via Granger Causality

Anil K. Seth

ARTIFICIAL LIFE (2010)

Review Computer Science, Artificial Intelligence

Enactive artificial intelligence: Investigating the systemic organization of life and mind

Tom Froese et al.

ARTIFICIAL INTELLIGENCE (2009)

Article Biology

Autonomy: An information theoretic perspective

Nils Bertschinger et al.

BIOSYSTEMS (2008)

Article Physics, Multidisciplinary

Measuring information transfer

T Schreiber

PHYSICAL REVIEW LETTERS (2000)