# Credal Networks under Maximum Entropy

arXiv: https://arxiv.org/abs/1301.3873 · HTML: https://mlsanity.com/paper/1301.3873/

## Key facts

- Cited by 13 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 16 Jan 2013.

## Built on by (most cited first, 13 of 13)

- [Text2Reward: Reward Shaping with Language Models for Reinforcement Learning](https://mlsanity.com/paper/2309.11489/) (2023)
- [Language Reward Modulation for Pretraining Reinforcement Learning](https://mlsanity.com/paper/2308.12270/) (2023)
- [Energy-Based Imitation Learning](https://mlsanity.com/paper/2004.09395/) (2020)
- [PARL: A Unified Framework for Policy Alignment in Reinforcement Learning from Human Feedback](https://mlsanity.com/paper/2308.02585/) (2023)
- [Maximum entropy GFlowNets with soft Q-learning](https://mlsanity.com/paper/2312.14331/) (2023)
- [A New Pairwise Deep Learning Feature For Environmental Microorganism Image Analysis](https://mlsanity.com/paper/2102.12147/) (2021)
- [Monte Carlo Tree Search with Boltzmann Exploration](https://mlsanity.com/paper/2404.07732/) (2024)
- [Soft Policy Optimization: Online Off-Policy RL for Sequence Models](https://mlsanity.com/paper/2503.05453/) (2025)
- [Distilling Calibration via Conformalized Credal Inference](https://mlsanity.com/paper/2501.06066/) (2025)
- [ELA: Exploited Level Augmentation for Offline Learning in Zero-Sum Games](https://mlsanity.com/paper/2402.18617/) (2024)
- [Learning to Route via Theory-Guided Residual Network](https://mlsanity.com/paper/2105.08279/) (2021)
- [Reward Learning using Structural Motifs in Inverse Reinforcement Learning](https://mlsanity.com/paper/2209.13489/) (2022)
- [Sample Complexity of Preference-Based Nonparametric Off-Policy Evaluation with Deep Networks](https://mlsanity.com/paper/2310.10556/) (2023)

## Abstract (arXiv)

We apply the principle of maximum entropy to select a unique joint probability distribution from the set of all joint probability distributions specified by a credal network. In detail, we start by showing that the unique joint distribution of a Bayesian tree coincides with the maximum entropy model of its conditional distributions. This result, however, does not hold anymore for general Bayesian networks. We thus present a new kind of maximum entropy models, which are computed sequentially. We then show that for all general Bayesian networks, the sequential maximum entropy model coincides with the unique joint distribution. Moreover, we apply the new principle of sequential maximum entropy to interval Bayesian networks and more generally to credal networks. We especially show that this application is equivalent to a number of small local entropy maximizations.