Towards Explainable Strategy Templates using NLP Transformers
This work addresses the need for explainable AI in negotiation systems for non-experts, but it is incremental as it builds on existing NLP and DRL techniques without introducing a new paradigm.
The paper tackled the problem of making Deep Reinforcement Learning strategies in automated agent negotiation comprehensible to non-experts by transforming mathematical strategy templates into natural language explanations using NLP and Transformers, resulting in a method that generates user-friendly English narratives through parsing, semantic interpretation, rule-based generation, and GPT refinement.
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.