English
Related papers

Related papers: Reward-Balancing for Statistical Spoken Dialogue S…

200 papers

Large language models are typically aligned with human preferences by optimizing $\textit{reward models}$ (RMs) fitted to human feedback. However, human preferences are multi-faceted, and it is increasingly common to derive reward from a…

We describe a two-step approach for dialogue management in task-oriented spoken dialogue systems. A unified neural network framework is proposed to enable the system to first learn by supervision from a set of dialogue data and then…

Computation and Language · Computer Science 2016-06-09 Pei-Hao Su , Milica Gasic , Nikola Mrksic , Lina Rojas-Barahona , Stefan Ultes , David Vandyke , Tsung-Hsien Wen , Steve Young

This paper describes a novel method by which a spoken dialogue system can learn to choose an optimal dialogue strategy from its experience interacting with human users. The method is based on a combination of reinforcement learning and…

Artificial Intelligence · Computer Science 2011-06-02 M. A. Walker

End-to-end multi-task dialogue systems are usually designed with separate modules for the dialogue pipeline. Among these, the policy module is essential for deciding what to do in response to user input. This policy is trained by…

Computation and Language · Computer Science 2024-03-27 Navin Kamuni , Hardik Shah , Sathishkumar Chintala , Naveen Kunchakuri , Sujatha Alla Old Dominion

Reinforcement learning has emerged as an important approach for autonomous driving. A reward function is used in reinforcement learning to establish the learned skill objectives and guide the agent toward the optimal policy. Since…

Robotics · Computer Science 2026-03-05 Ahmed Abouelazm , Jonas Michel , J. Marius Zoellner

When learning task-oriented dialogue (ToD) agents, reinforcement learning (RL) techniques can naturally be utilized to train dialogue strategies to achieve user-specific goals. Prior works mainly focus on adopting advanced RL techniques to…

Computation and Language · Computer Science 2023-02-22 Yihao Feng , Shentao Yang , Shujian Zhang , Jianguo Zhang , Caiming Xiong , Mingyuan Zhou , Huan Wang

Dialog policies, which determine a system's action based on the current state at each dialog turn, are crucial to the success of the dialog. In recent years, reinforcement learning (RL) has emerged as a promising option for dialog policy…

Mathematical reasoning is a key benchmark for large language models. Reinforcement learning is a standard post-training mechanism for improving the reasoning capabilities of large language models, yet performance remains sensitive to the…

Computation and Language · Computer Science 2026-05-11 Arash Ahmadi , Sarah Sharif , Yaser , Banad

Dialogue Policy Learning is a key component in a task-oriented dialogue system (TDS) that decides the next action of the system given the dialogue state at each turn. Reinforcement Learning (RL) is commonly chosen to learn the dialogue…

Computation and Language · Computer Science 2023-11-09 Wai-Chung Kwan , Hongru Wang , Huimin Wang , Kam-Fai Wong

Task-oriented dialogue (TOD) system is designed to accomplish user-defined tasks through dialogues. The TOD system has progressed towards end-to-end modeling by leveraging pre-trained large language models. Fine-tuning the pre-trained…

Computation and Language · Computer Science 2024-11-11 Dharmendra Prajapat , Durga Toshniwal

Learning suitable and well-performing dialogue behaviour in statistical spoken dialogue systems has been in the focus of research for many years. While most work which is based on reinforcement learning employs an objective measure like…

Computation and Language · Computer Science 2020-01-22 Stefan Ultes

To train a statistical spoken dialogue system (SDS) it is essential that an accurate method for measuring task success is available. To date training has relied on presenting a task to either simulated or paid users and inferring the…

Machine Learning · Computer Science 2015-08-17 Pei-Hao Su , David Vandyke , Milica Gasic , Dongho Kim , Nikola Mrksic , Tsung-Hsien Wen , Steve Young

Reinforcement learning (RL) methods usually treat reward functions as black boxes. As such, these methods must extensively interact with the environment in order to discover rewards and optimal policies. In most RL applications, however,…

Machine Learning · Computer Science 2022-01-19 Rodrigo Toro Icarte , Toryn Q. Klassen , Richard Valenzano , Sheila A. McIlraith

The optimal objective is a fundamental aspect of reinforcement learning (RL), as it determines how policies are evaluated and optimized. While total return maximization is the ideal objective in RL, discounted return maximization is the…

Machine Learning · Computer Science 2025-03-19 Shuyu Yin , Fei Wen , Peilin Liu , Tao Luo

Human conversation is inherently complex, often spanning many different topics/domains. This makes policy learning for dialogue systems very challenging. Standard flat reinforcement learning methods do not provide an efficient framework for…

In traditional reinforcement learning (RL), the learner aims to solve a single objective optimization problem: find the policy that maximizes expected reward. However, in many real-world settings, it is important to optimize over multiple…

Machine Learning · Computer Science 2025-02-18 Eric Eaton , Marcel Hussing , Michael Kearns , Aaron Roth , Sikata Bela Sengupta , Jessica Sorrell

Representing a dialog policy as a recurrent neural network (RNN) is attractive because it handles partial observability, infers a latent representation of state, and can be optimized with supervised learning (SL) or reinforcement learning…

Artificial Intelligence · Computer Science 2016-12-20 Kavosh Asadi , Jason D. Williams

Reinforcement learning algorithms are fundamental to align large language models with human preferences and to enhance their reasoning capabilities. However, current reinforcement learning algorithms often suffer from training instability…

Machine Learning · Computer Science 2025-06-05 Yaru Hao , Li Dong , Xun Wu , Shaohan Huang , Zewen Chi , Furu Wei

Finding optimal policies which maximize long term rewards of Markov Decision Processes requires the use of dynamic programming and backward induction to solve the Bellman optimality equation. However, many real-world problems require…

Machine Learning · Computer Science 2023-01-10 Mridul Agarwal , Vaneet Aggarwal

In spoken dialogue systems, we aim to deploy artificial intelligence to build automated dialogue agents that can converse with humans. A part of this effort is the policy optimisation task, which attempts to find a policy describing how to…

Computation and Language · Computer Science 2018-02-13 Gellért Weisz , Paweł Budzianowski , Pei-Hao Su , Milica Gašić