# Investigating Reinforcement Learning for Communication Strategies in a Task-Initiative Setting

arXiv: https://arxiv.org/abs/2308.01479 · HTML: https://mlsanity.com/paper/2308.01479/

## Key facts

- Cited by 1 papers in the map (data through 14 Oct 2026).
- Builds on 6 of its 30 references that are in the map.
- First posted on arXiv 3 Aug 2023.

## Builds on (most cited first, 6 of 6)

- [Playing Atari with Deep Reinforcement Learning](https://mlsanity.com/paper/1312.5602/) (2013)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [A User Simulator for Task-Completion Dialogues](https://mlsanity.com/paper/1612.05688/) (2016)
- [Colors in Context: A Pragmatic Neural Model for Grounded Language Understanding](https://mlsanity.com/paper/1703.10186/) (2017)
- [How to Build User Simulators to Train RL-based Dialog Systems](https://mlsanity.com/paper/1909.01388/) (2019)
- [Discourse Coherence, Reference Grounding and Goal Oriented Dialogue](https://mlsanity.com/paper/2007.04428/) (2020)

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

- [Taking Action Towards Graceful Interaction: The Effects of Performing Actions on Modelling Policies for Instruction Clarification Requests](https://mlsanity.com/paper/2401.17039/) (2024)

## Abstract (arXiv)

Many conversational domains require the system to present nuanced information to users. Such systems must follow up what they say to address clarification questions and repair misunderstandings. In this work, we explore this interactive strategy in a referential communication task. Using simulation, we analyze the communication trade-offs between initial presentation and subsequent followup as a function of user clarification strategy, and compare the performance of several baseline strategies to policies derived by reinforcement learning. We find surprising advantages to coherence-based representations of dialogue strategy, which bring minimal data requirements, explainable choices, and strong audit capabilities, but incur little loss in predicted outcomes across a wide range of user models.