# Learning Rhetorical Structure Theory-based descriptions of observed behaviour

arXiv: https://arxiv.org/abs/2206.12294 · HTML: https://mlsanity.com/paper/2206.12294/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 4 of its 52 references that are in the map.
- First posted on arXiv 24 Jun 2022.

## Builds on (most cited first, 4 of 4)

- [Explanation in Artificial Intelligence: Insights from the Social Sciences](https://mlsanity.com/paper/1706.07269/) (2017)
- [Curiosity-driven Exploration by Self-supervised Prediction](https://mlsanity.com/paper/1705.05363/) (2017)
- [A Framework for Understanding Sources of Harm throughout the Machine Learning Life Cycle](https://mlsanity.com/paper/1901.10002/) (2019)
- [Attention-based Curiosity-driven Exploration in Deep Reinforcement Learning](https://mlsanity.com/paper/1910.10840/) (2019)

## Abstract (arXiv)

In a previous paper, we have proposed a set of concepts, axiom schemata and algorithms that can be used by agents to learn to describe their behaviour, goals, capabilities, and environment. The current paper proposes a new set of concepts, axiom schemata and algorithms that allow the agent to learn new descriptions of an observed behaviour (e.g., perplexing actions), of its actor (e.g., undesired propositions or actions), and of its environment (e.g., incompatible propositions). Each learned description (e.g., a certain action prevents another action from being performed in the future) is represented by a relationship between entities (either propositions or actions) and is learned by the agent, just by observation, using domain-independent axiom schemata and or learning algorithms. The relations used by agents to represent the descriptions they learn were inspired on the Theory of Rhetorical Structure (RST). The main contribution of the paper is the relation family Although, inspired on the RST relation Concession. The accurate definition of the relations of the family Although involves a set of deontic concepts whose definition and corresponding algorithms are presented. The relations of the family Although, once extracted from the agent's observations, express surprise at the observed behaviour and, in certain circumstances, present a justification for it. The paper shows results of the presented proposals in a demonstration scenario, using implemented software.