Estimating Rationally Inattentive Utility Functions with Deep Clustering for Framing - Applications in YouTube Engagement Dynamics
Explore this paper's citation graph
Summary
This work considers a framework involving behavioral economics and machine learning, and presents a preference based inverse reinforcement learning algorithm to test for rational inattention, which imposes a Renyi mutual information constraint which impacts how the agent can select attention strategies to maximize their expected utility.
- Type
- preprint
- Published
- 2018-12-23
- Cited by
- 0
- References
- 44
- Access
- Open access
- OpenAlex
- https://openalex.org/W2905663220
- Semantic Scholar
- https://api.semanticscholar.org/CorpusID:56895328
Keywords
Computer science, Reinforcement learning, Mutual information, Artificial intelligence, Expected utility hypothesis
References
- Neural Network Learning: Theoretical Foundations
- Convexity/concavity of renyi entropy and α-mutual information
- A Primer on Neural Network Models for Natural Language Processing
- Fully convolutional networks for semantic segmentation
- On the Density of Families of Sets
- Implications of rational inattention
- How to Schedule Measurements of a Noisy Markov Chain in Decision Making?
- Extracting and composing robust features with denoising autoencoders
- Rényi Divergence and Kullback-Leibler Divergence
- Learning Deep Architectures for AI
- Dropout: a simple way to prevent neural networks from overfitting
- Rational Inattention to Discrete Choices: A New Foundation for the Multinomial Logit Model
- Revealed Preference and its Applications
- Revealed Preference, Rational Inattention, and Costly Information Acquisition
- A Testable Theory of Imperfect Perception
- Distributed Representations of Words and Phrases and their Compositionality
- Afriat's Theorem and Some Extensions to Choice Under Uncertainty
- Inattentive Valuation and Reference-Dependent Choice ∗
- Socially Adaptive Path Planning in Human Environments Using Inverse Reinforcement Learning
- Adaptive Caching in the YouTube Content Distribution Network: A Revealed Preference Game-Theoretic Learning Approach
Cited by
No citing papers recorded for this paper.
Related papers
- Approximations of Shannon Mutual Information for Discrete Variables with Applications to Neural Population Coding
- Approximations of Shannon Mutual Information for Discrete Variables with Applications to Neural Population Coding
- Investigation of Alternative Measures for Mutual Information
- Estimation-Theoretic Representation of Mutual Information
- S.21.04 The mechanism of action of deep brain stimulation: preclinical and clinical evidence
- Probing High-Order Dependencies With Information Theory
- Big Data Viewpoint On Channel Information Measures Based on ACE Algorithm
- Representation of Mutual Information Via Input Estimates
- Research on principles of information transmission using entropy and mutual information