# Towards Explainable Strategy Templates using NLP Transformers

arXiv: https://arxiv.org/abs/2311.14061 · HTML: https://mlsanity.com/paper/2311.14061/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 7 of its 23 references that are in the map.
- First posted on arXiv 23 Nov 2023.

## Builds on (most cited first, 7 of 7)

- [BERT: Pre-training of Deep Bidirectional Transformers for Language Understanding](https://mlsanity.com/paper/1810.04805/) (2018)
- [Language Models are Few-Shot Learners](https://mlsanity.com/paper/2005.14165/) (2020)
- [Exploring the Limits of Transfer Learning with a Unified Text-to-Text Transformer](https://mlsanity.com/paper/1910.10683/) (2019)
- [RoBERTa: A Robustly Optimized BERT Pretraining Approach](https://mlsanity.com/paper/1907.11692/) (2019)
- [FinRL: Deep Reinforcement Learning Framework to Automate Trading in Quantitative Finance](https://mlsanity.com/paper/2111.09395/) (2021)
- [Deep Learnable Strategy Templates for Multi-Issue Bilateral Negotiation](https://mlsanity.com/paper/2201.02455/) (2022)
- [Learnable Strategies for Bilateral Agent Negotiation over Multiple Issues](https://mlsanity.com/paper/2009.08302/) (2020)

## Built on by (most cited first, 1 of 1)

- [Explainability in Practice: A Survey of Explainable NLP Across Various Domains](https://mlsanity.com/paper/2502.00837/) (2025)

## Abstract (arXiv)

This paper bridges the gap between mathematical heuristic strategies learned from Deep Reinforcement Learning (DRL) in automated agent negotiation, and comprehensible, natural language explanations. Our aim is to make these strategies more accessible to non-experts. By leveraging traditional Natural Language Processing (NLP) techniques and Large Language Models (LLMs) equipped with Transformers, we outline how parts of DRL strategies composed of parts within strategy templates can be transformed into user-friendly, human-like English narratives. To achieve this, we present a top-level algorithm that involves parsing mathematical expressions of strategy templates, semantically interpreting variables and structures, generating rule-based primary explanations, and utilizing a Generative Pre-trained Transformer (GPT) model to refine and contextualize these explanations. Subsequent customization for varied audiences and meticulous validation processes in an example illustrate the applicability and potential of this approach.