# An Information-theoretic On-line Learning Principle for Specialization in Hierarchical Decision-Making Systems

arXiv: https://arxiv.org/abs/1907.11452 · HTML: https://mlsanity.com/paper/1907.11452/

## Key facts

- Cited by 7 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 26 Jul 2019.

## Built on by (most cited first, 7 of 7)

- [Hierarchically Structured Task-Agnostic Continual Learning](https://mlsanity.com/paper/2211.07725/) (2022)
- [Mixture-of-Variational-Experts for Continual Learning](https://mlsanity.com/paper/2110.12667/) (2021)
- [Mixture-of-Experts under Finite-Rate Gating: Communication--Generalization Trade-offs](https://mlsanity.com/paper/2602.15091/) (2026)
- [Variational Inference for Model-Free and Model-Based Reinforcement Learning](https://mlsanity.com/paper/2209.01693/) (2022)
- [Information Theoretical Importance Sampling Clustering](https://mlsanity.com/paper/2302.04421/) (2023)
- [An information-theoretic learning model based on importance sampling](https://mlsanity.com/paper/2302.04438/) (2023)
- [Exploiting Expertise of Non-Expert and Diverse Agents in Social Bandit Learning: A Free Energy Approach](https://mlsanity.com/paper/2603.11757/) (2026)

## Abstract (arXiv)

Information-theoretic bounded rationality describes utility-optimizing decision-makers whose limited information-processing capabilities are formalized by information constraints. One of the consequences of bounded rationality is that resource-limited decision-makers can join together to solve decision-making problems that are beyond the capabilities of each individual. Here, we study an information-theoretic principle that drives division of labor and specialization when decision-makers with information constraints are joined together. We devise an on-line learning rule of this principle that learns a partitioning of the problem space such that it can be solved by specialized linear policies. We demonstrate the approach for decision-making problems whose complexity exceeds the capabilities of individual decision-makers, but can be solved by combining the decision-makers optimally. The strength of the model is that it is abstract and principled, yet has direct applications in classification, regression, reinforcement learning and adaptive control.