# Reinforcement Learning for Personalized Dialogue Management

arXiv: https://arxiv.org/abs/1908.00286 · HTML: https://mlsanity.com/paper/1908.00286/

## Key facts

- Cited by 6 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 1 Aug 2019.

## Built on by (most cited first, 6 of 6)

- [CharacterEval: A Chinese Benchmark for Role-Playing Conversational Agent Evaluation](https://mlsanity.com/paper/2401.01275/) (2024)
- [Personalisation within bounds: A risk taxonomy and policy framework for the alignment of large language models with personalised feedback](https://mlsanity.com/paper/2303.05453/) (2023)
- [The Past, Present and Better Future of Feedback Learning in Large Language Models for Subjective Human Preferences and Values](https://mlsanity.com/paper/2310.07629/) (2023)
- [Crafting Customisable Characters with LLMs: A Persona-Driven Role-Playing Agent Framework](https://mlsanity.com/paper/2406.17962/) (2024)
- [Conformal Intent Classification and Clarification for Fast and Accurate Intent Recognition](https://mlsanity.com/paper/2403.18973/) (2024)
- [Are LLMs Good Financial User Simulators? Multi-view Investor Logic Alignment (MILA)](https://mlsanity.com/paper/2609.15727/) (2026)

## Abstract (arXiv)

Language systems have been of great interest to the research community and have recently reached the mass market through various assistant platforms on the web. Reinforcement Learning methods that optimize dialogue policies have seen successes in past years and have recently been extended into methods that personalize the dialogue, e.g. take the personal context of users into account. These works, however, are limited to personalization to a single user with whom they require multiple interactions and do not generalize the usage of context across users. This work introduces a problem where a generalized usage of context is relevant and proposes two Reinforcement Learning (RL)-based approaches to this problem. The first approach uses a single learner and extends the traditional POMDP formulation of dialogue state with features that describe the user context. The second approach segments users by context and then employs a learner per context. We compare these approaches in a benchmark of existing non-RL and RL-based methods in three established and one novel application domain of financial product recommendation. We compare the influence of context and training experiences on performance and find that learning approaches generally outperform a handcrafted gold standard.