# Learning Robust Dialog Policies in Noisy Environments

arXiv: https://arxiv.org/abs/1712.04034 · HTML: https://mlsanity.com/paper/1712.04034/

## Key facts

- Cited by 5 papers in the map (data through 14 Oct 2026).
- First posted on arXiv 11 Dec 2017.

## Built on by (most cited first, 5 of 5)

- [A Survey on Deep Reinforcement Learning for Audio-Based Applications](https://mlsanity.com/paper/2101.00240/) (2021)
- [Alexa Conversations: An Extensible Data-driven Approach for Building Task-oriented Dialogue Systems](https://mlsanity.com/paper/2104.09088/) (2021)
- [Knowledge Grounded Conversational Symptom Detection with Graph Memory Networks](https://mlsanity.com/paper/2101.09773/) (2021)
- [Teaching Models new APIs: Domain-Agnostic Simulators for Task Oriented Dialogue](https://mlsanity.com/paper/2110.06905/) (2021)
- [Reinforcement Learning of Multi-Domain Dialog Policies Via Action Embeddings](https://mlsanity.com/paper/2207.00468/) (2022)

## Abstract (arXiv)

Modern virtual personal assistants provide a convenient interface for completing daily tasks via voice commands. An important consideration for these assistants is the ability to recover from automatic speech recognition (ASR) and natural language understanding (NLU) errors. In this paper, we focus on learning robust dialog policies to recover from these errors. To this end, we develop a user simulator which interacts with the assistant through voice commands in realistic scenarios with noisy audio, and use it to learn dialog policies through deep reinforcement learning. We show that dialogs generated by our simulator are indistinguishable from human generated dialogs, as determined by human evaluators. Furthermore, preliminary experimental results show that the learned policies in noisy environments achieve the same execution success rate with fewer dialog turns compared to fixed rule-based policies.