# Causal-aware Safe Policy Improvement for Task-oriented dialogue

arXiv: https://arxiv.org/abs/2103.06370 · HTML: https://mlsanity.com/paper/2103.06370/

## Key facts

- Cited by 4 papers in the map (data through 14 Oct 2026).
- Builds on 22 of its 30 references that are in the map.
- First posted on arXiv 10 Mar 2021.

## Builds on (most cited first, 22 of 22)

- [BART: Denoising Sequence-to-Sequence Pre-training for Natural Language Generation, Translation, and Comprehension](https://mlsanity.com/paper/1910.13461/) (2019)
- [Deep reinforcement learning from human preferences](https://mlsanity.com/paper/1706.03741/) (2017)
- [Trust Region Policy Optimization](https://mlsanity.com/paper/1502.05477/) (2015)
- [MultiWOZ -- A Large-Scale Multi-Domain Wizard-of-Oz Dataset for Task-Oriented Dialogue Modelling](https://mlsanity.com/paper/1810.00278/) (2018)
- [Towards Scalable Multi-domain Conversational Agents: The Schema-Guided Dialogue Dataset](https://mlsanity.com/paper/1909.05855/) (2019)
- [Overcoming Exploration in Reinforcement Learning with Demonstrations](https://mlsanity.com/paper/1709.10089/) (2017)
- [A Simple Language Model for Task-Oriented Dialogue](https://mlsanity.com/paper/2005.00796/) (2020)
- [Leveraging Demonstrations for Deep Reinforcement Learning on Robotics Problems with Sparse Rewards](https://mlsanity.com/paper/1707.08817/) (2017)
- [Data-Efficient Off-Policy Policy Evaluation for Reinforcement Learning](https://mlsanity.com/paper/1604.00923/) (2016)
- [Way Off-Policy Batch Deep Reinforcement Learning of Implicit Human Preferences in Dialog](https://mlsanity.com/paper/1907.00456/) (2019)
- [A Network-based End-to-End Trainable Task-oriented Dialogue System](https://mlsanity.com/paper/1604.04562/) (2016)
- [Go-Explore: a New Approach for Hard-Exploration Problems](https://mlsanity.com/paper/1901.10995/) (2019)
- [MinTL: Minimalist Transfer Learning for Task-Oriented Dialogue Systems](https://mlsanity.com/paper/2009.12005/) (2020)
- [Playing hard exploration games by watching YouTube](https://mlsanity.com/paper/1805.11592/) (2018)
- [Task-Oriented Dialog Systems that Consider Multiple Appropriate Responses under the Same Context](https://mlsanity.com/paper/1911.10484/) (2019)
- [SOLOIST: Building Task Bots at Scale with Transfer Learning and Machine Teaching](https://mlsanity.com/paper/2005.05298/) (2020)
- [Rethinking Action Spaces for Reinforcement Learning in End-to-end Dialog Agents with Latent Variable Models](https://mlsanity.com/paper/1902.08858/) (2019)
- [Semantically Conditioned Dialog Response Generation via Hierarchical Disentangled Self-Attention](https://mlsanity.com/paper/1905.12866/) (2019)
- [Structured Fusion Networks for Dialog](https://mlsanity.com/paper/1907.10016/) (2019)
- [Learning to Generalize from Sparse and Underspecified Rewards](https://mlsanity.com/paper/1902.07198/) (2019)
- [LAVA: Latent Action Spaces via Variational Auto-encoding for Dialogue Policy Optimization](https://mlsanity.com/paper/2011.09378/) (2020)
- [Modelling Hierarchical Structure between Dialogue Policy and Natural Language Generator with Option Framework for Task-oriented Dialogue System](https://mlsanity.com/paper/2006.06814/) (2020)

## Built on by (most cited first, 4 of 4)

- [A Survey on Recent Advances in LLM-Based Multi-turn Dialogue Systems](https://mlsanity.com/paper/2402.18013/) (2024)
- [Leftover Lunch: Advantage-based Offline Reinforcement Learning for Language Models](https://mlsanity.com/paper/2305.14718/) (2023)
- [KRLS: Improving End-to-End Response Generation in Task Oriented Dialog with Reinforced Keywords Learning](https://mlsanity.com/paper/2211.16773/) (2022)
- [CSS: Combining Self-training and Self-supervised Learning for Few-shot Dialogue State Tracking](https://mlsanity.com/paper/2210.05146/) (2022)

## Abstract (arXiv)

The recent success of reinforcement learning's (RL) in solving complex tasks is most often attributed to its capacity to explore and exploit an environment where it has been trained. Sample efficiency is usually not an issue since cheap simulators are available to sample data on-policy. On the other hand, task oriented dialogues are usually learnt from offline data collected using human demonstrations. Collecting diverse demonstrations and annotating them is expensive. Unfortunately, use of RL methods trained on off-policy data are prone to issues of bias and generalization, which are further exacerbated by stochasticity in human response and non-markovian belief state of a dialogue management system. To this end, we propose a batch RL framework for task oriented dialogue policy learning: causal aware safe policy improvement (CASPI). This method gives guarantees on dialogue policy's performance and also learns to shape rewards according to intentions behind human responses, rather than just mimicking demonstration data; this couple with batch-RL helps overall with sample efficiency of the framework. We demonstrate the effectiveness of this framework on a dialogue-context-to-text Generation and end-to-end dialogue task of the Multiwoz2.0 dataset. The proposed method outperforms the current state of the art on these metrics, in both case. In the end-to-end case, our method trained only on 10% of the data was able to out perform current state in three out of four evaluation metrics.